Explorez tous les épisodes du podcast TalkRL: The Reinforcement Learning Podcast

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at NeurIPS 2024 in Vancouver BC Canada.   

Featuring  

• Claire Bizon Monroc from Inria: WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control  
• Andrew Wagenmaker from UC Berkeley: Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL  
• Harley Wiltzer from MILA: Foundations of Multivariate Distributional Reinforcement Learning  
• Vinzenz Thoma from ETH AI Center: Contextual Bilevel Reinforcement Learning for Incentive Alignment  
• Haozhe (Tony) Chen & Ang (Leon) Li from Columbia: QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers  

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at NeurIPS 2024 in Vancouver BC Canada.   

Featuring  

• Jonathan Cook from University of Oxford: Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning  
• Yifei Zhou from Berkeley AI Research: DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning  
• Rory Young from University of Glasgow: Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach  
• Glen Berseth from MILA: Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn  
• Alexander Rutherford from University of Oxford: JaxMARL: Multi-Agent RL Environments and Algorithms in JAX  

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at NeurIPS 2024 in Vancouver BC Canada.   

Featuring  

• Jiaheng Hu of University of Texas: Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning  
• Skander Moalla of EPFL: No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO  
• Adil Zouitine of IRT Saint Exupery/Hugging Face : Time-Constrained Robust MDPs  
• Soumyendu Sarkar of HP Labs : SustainDC: Benchmarking for Sustainable Data Center Control  
• Matteo Bettini of Cambridge University: BenchMARL: Benchmarking Multi-Agent Reinforcement Learning  
• Michael Bowling of U Alberta : Beyond Optimism: Exploration With Partially Observable Rewards  

Abhishek Naik was a student at University of Alberta and Alberta Machine Intelligence Institute, and he just finished his PhD in reinforcement learning, working with Rich Sutton.  Now he is a postdoc fellow at the National Research Council of Canada, where he does AI research on Space applications. 

Featured References 

Reinforcement Learning for Continuing Problems Using Average Reward
Abhishek Naik Ph.D. dissertation 2024 

Reward Centering
Abhishek Naik, Yi Wan, Manan Tomar, Richard S. Sutton 2024   

Learning and Planning in Average-Reward Markov Decision Processes
Yi Wan, Abhishek Naik, Richard S. Sutton 2020 

Discounted Reinforcement Learning Is Not an Optimization Problem 
Abhishek Naik, Roshan Shariff, Niko Yasui, Hengshuai Yao, Richard S. Sutton 2019  

Additional References 

• Explaining dopamine through prediction errors and beyond, Gershman et al 2024 (proposes Differential-TD-like learning mechanism in the brain around Box 4)  

What do RL researchers complain about after hours at the bar?  In this "Hot takes" episode, we find out!  

Recorded at The Pearl in downtown Vancouver, during the RL meetup after a day of Neurips 2024.  

Special thanks to "David Beckham" for the inspiration :)  

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at RLC 2024 in Amherst MA.   

Featuring:  

• 0:01 David Radke of the Chicago Blackhawks NHL on RL for professional sports  
• 0:56 Abhishek Naik from the National Research Council on Continuing RL and Average Reward  
• 2:42 Daphne Cornelisse from NYU on Autonomous Driving and Multi-Agent RL  
• 08:58 Shray Bansal from Georgia Tech on Cognitive Bias for Human AI Ad hoc Teamwork  
• 10:21 Claas Voelcker from University of Toronto on Can we hop in general?  
• 11:23 Brent Venable from The Institute for Human & Machine Cognition on Cooperative information dissemination  

  
  

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at RLC 2024 in Amherst MA.   

Featuring:  

• 0:01  David Abel from DeepMind on 3 Dogmas of RL  
• 0:55 Kevin Wang from Brown on learning variable depth search for MCTS  
• 2:17 Ashwin Kumar from Washington University in St Louis on fairness in resource allocation  
• 3:36 Prabhat Nagarajan from UAlberta on Value overestimation  

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at RLC 2024 in Amherst MA.  

Featuring:  

• 0:01 Kris De Asis from Openmind on Time Discretization  
• 2:23 Anna Hakhverdyan from U of Alberta on Online Hyperparameters  
• 3:59 Dilip Arumugam from Princeton on Information Theory and Exploration  
• 5:04 Micah Carroll from UC Berkeley on Changing preferences and AI alignment  

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at RLC 2024 in Amherst MA.  

Featuring:  

• 0:01 Hector Kohler from Centre Inria de l'Université de Lille with "Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning"  
• 2:29 Quentin Delfosse from TU Darmstadt on "Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents"  
• 4:15 Sonja Johnson-Yu from Harvard on "Understanding biological active sensing behaviors by interpreting learned artificial agent policies"  
• 6:42 Jannis Blüml from TU Darmstadt on "OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments"  
• 8:20 Cameron Allen from UC Berkeley on "Resolving Partial Observability in Decision Processes via the Lambda Discrepancy"  
• 9:48 James Staley from Tufts on "Agent-Centric Human Demonstrations Train World Models"  
• 14:54 Jonathan Li from Rensselaer Polytechnic Institute  

Posters and Hallway episodes are short interviews and poster summaries.  Recorded at RLC 2024 in Amherst MA.  

Featuring:  

• 0:01 Ann Huang from Harvard on Learning Dynamics and the Geometry of Neural Dynamics in Recurrent Neural Controllers  
• 1:37 Jannis Blüml from TU Darmstadt on HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning  
• 3:13 Benjamin Fuhrer from NVIDIA on Gradient Boosting Reinforcement Learning  
• 3:54 Paul Festor from Imperial College London on Evaluating the impact of explainable RL on physician decision-making in high-fidelity simulations: insights from eye-tracking metrics  

Finale Doshi-Velez is a Professor at the Harvard Paulson School of Engineering and Applied Sciences. 

This off-the-cuff interview was recorded at UMass Amherst during the workshop day of RL Conference on August 9th 2024.   

Host notes: I've been a fan of some of Prof Doshi-Velez' past work on clinical RL and hoped to feature her for some time now, so I jumped at the chance to get a few minutes of her thoughts -- even though you can tell I was not prepared and a bit flustered tbh.  Thanks to Prof Doshi-Velez for taking a moment for this, and I hope to cross paths in future for a more in depth interview.

References  

• Finale Doshi-Velez Homepage @ Harvard  
• Finale Doshi-Velez on Google Scholar  

Thanks to Professor Silver for permission to record this discussion after his RLC 2024 keynote lecture.   

Recorded at UMass Amherst during RCL 2024.

Due to the live recording environment, audio quality varies.  We publish this audio in its raw form to preserve the authenticity and immediacy of the discussion.   

References  

• AlphaProof announcement on DeepMind's blog
• Discovering Reinforcement Learning Algorithms, Oh et al  -- His keynote at RLC 2024 referred to more recent update to this work, yet to be published  
• Reinforcement Learning Conference 2024  
• David Silver on Google Scholar  

David Silver is a principal research scientist at DeepMind and a professor at University College London. 

This interview was recorded at UMass Amherst during RLC 2024.   

References  

• Discovering Reinforcement Learning Algorithms, Oh et al  -- His keynote at RLC 2024 referred to more recent update to this work, yet to be published  
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm, Silver et al 2017 -- the AlphaZero algo was used   in his recent work on AlphaProof  
• AlphaProof on the DeepMind blog 
• AlphaFold on the DeepMind blog 
• Reinforcement Learning Conference 2024  
• David Silver on Google Scholar  

Dr. Vincent Moens is an Applied Machine Learning Research Scientist at Meta, and an author of TorchRL and TensorDict in pytorch. 

Featured References

TorchRL: A data-driven decision-making library for PyTorch
Albert Bou, Matteo Bettini, Sebastian Dittert, Vikash Kumar, Shagun Sodhani, Xiaomeng Yang, Gianni De Fabritiis, Vincent Moens 

Additional References  

• TorchRL on github  
• TensorDict Documentation  

Arash Ahmadian is a Researcher at Cohere and Cohere For AI focussed on Preference Training of large language models. He’s also a researcher at the Vector Institute of AI.

Featured Reference

Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Arash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, Sara Hooker

Additional References

• Self-Rewarding Language Models, Yuan et al 2024
• Reinforcement Learning: An Introduction, Sutton and Barto 1992
• Learning from Delayed Rewards, Chris Watkins 1989
• Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning, Williams 1992

Glen Berseth is an assistant professor at the Université de Montréal, a core academic member of the Mila - Quebec AI Institute, a Canada CIFAR AI chair, member l'Institute Courtios, and co-director of the Robotics and Embodied AI Lab (REAL). 

Featured Links 

Reinforcement Learning Conference 

Closing the Gap between TD Learning and Supervised Learning--A Generalisation Point of View
Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach

Ian Osband is a Research scientist at OpenAI (ex DeepMind, Stanford) working on decision making under uncertainty.  

We spoke about: 

- Information theory and RL 

- Exploration, epistemic uncertainty and joint predictions 

- Epistemic Neural Networks and scaling to LLMs 

Featured References 

Reinforcement Learning, Bit by Bit 
Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla, Morteza Ibrahimi, Ian Osband, Zheng Wen 

From Predictions to Decisions: The Importance of Joint Predictive Distributions 

Zheng Wen, Ian Osband, Chao Qin, Xiuyuan Lu, Morteza Ibrahimi, Vikranth Dwaracherla, Mohammad Asghari, Benjamin Van Roy  

Epistemic Neural Networks 

Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy  

Approximate Thompson Sampling via Epistemic Neural Networks 

Ian Osband, Zheng Wen, Seyed Mohammad Asghari, Vikranth Dwaracherla, Morteza Ibrahimi, Xiuyuan Lu, Benjamin Van Roy 

Additional References  

• Thesis defence, Ian Osband 
• Homepage, Ian Osband 
• Epistemic Neural Networks at Stanford RL Forum 
• Behaviour Suite for Reinforcement Learning, Osband et al 2019 
• Efficient Exploration for LLMs, Dwaracherla et al 2024 

Sharath Chandra Raparthy on In-Context Learning for Sequential Decision Tasks, GFlowNets, and more!  

Sharath Chandra Raparthy is an AI Resident at FAIR at Meta, and did his Master's at Mila.  

Featured Reference 

Generalization to New Sequential Decision Making Tasks with In-Context Learning   
Sharath Chandra Raparthy , Eric Hambro, Robert Kirk , Mikael Henaff, , Roberta Raileanu 

Additional References  

• Sharath Chandra Raparthy Homepage  
• Human-Timescale Adaptation in an Open-Ended Task Space, Adaptive Agent Team 2023
• Data Distributional Properties Drive Emergent In-Context Learning in Transformers, Chan et al 2022  
• Decision Transformer: Reinforcement Learning via Sequence Modeling, Chen et al  2021

Pierluca D'Oro and Martin Klissarov on Motif and RLAIF, Noisy Neighborhoods and Return Landscapes, and more!  

Pierluca D'Oro is PhD student at Mila and visiting researcher at Meta.

Martin Klissarov is a PhD student at Mila and McGill and research scientist intern at Meta.  

Featured References 

Motif: Intrinsic Motivation from Artificial Intelligence Feedback 
Martin Klissarov*, Pierluca D'Oro*, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang, Mikael Henaff 

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control 
Nate Rahn*, Pierluca D'Oro*, Harley Wiltzer, Pierre-Luc Bacon, Marc G. Bellemare 

To keep doing RL research, stop calling yourself an RL researcher
Pierluca D'Oro 

Martin Riedmiller of Google DeepMind on controlling nuclear fusion plasma in a tokamak with RL, the original Deep Q-Network, Neural Fitted Q-Iteration, Collect and Infer, AGI for control systems, and tons more!  

Martin Riedmiller is a research scientist and team lead at DeepMind.   

Featured References   

Magnetic control of tokamak plasmas through deep reinforcement learning 
Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan Tracey, Francesco Carpanese, Timo Ewalds, Roland Hafner, Abbas Abdolmaleki, Diego de las Casas, Craig Donner, Leslie Fritz, Cristian Galperti, Andrea Huber, James Keeling, Maria Tsimpoukelli, Jackie Kay, Antoine Merle, Jean-Marc Moret, Seb Noury, Federico Pesamosca, David Pfau, Olivier Sauter, Cristian Sommariva, Stefano Coda, Basil Duval, Ambrogio Fasoli, Pushmeet Kohli, Koray Kavukcuoglu, Demis Hassabis & Martin Riedmiller

Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis 

Neural fitted Q iteration–first experiences with a data efficient neural reinforcement learning method 
Martin Riedmiller  

Max Schwarzer is a PhD student at Mila, with Aaron Courville and Marc Bellemare, interested in RL scaling, representation learning for RL, and RL for science.  Max spent the last 1.5 years at Google Brain/DeepMind, and is now at Apple Machine Learning Research.   

Featured References

Bigger, Better, Faster: Human-level Atari with human-level efficiency 
Max Schwarzer, Johan Obando-Ceron, Aaron Courville, Marc Bellemare, Rishabh Agarwal, Pablo Samuel Castro 

Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
Pierluca D'Oro, Max Schwarzer, Evgenii Nikishin, Pierre-Luc Bacon, Marc G Bellemare, Aaron Courville 

The Primacy Bias in Deep Reinforcement Learning
Evgenii Nikishin, Max Schwarzer, Pierluca D'Oro, Pierre-Luc Bacon, Aaron Courville 


Additional References   

• Rainbow: Combining Improvements in Deep Reinforcement Learning, Hessel et al 2017  
• When to use parametric models in reinforcement learning? Hasselt et al 2019 
• Data-Efficient Reinforcement Learning with Self-Predictive Representations, Schwarzer et al 2020  
• Pretraining Representations for Data-Efficient Reinforcement Learning, Schwarzer et al 2021  

Julian Togelius is an Associate Professor of Computer Science and Engineering at NYU, and Cofounder and research director at modl.ai

Featured References  
Choose Your Weapon: Survival Strategies for Depressed AI Academics

Julian Togelius, Georgios N. Yannakakis

Learning Controllable 3D Level Generators

Zehua Jiang, Sam Earle, Michael Cerny Green, Julian Togelius

PCGRL: Procedural Content Generation via Reinforcement Learning

Ahmed Khalifa, Philip Bontrager, Sam Earle, Julian Togelius

Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation

Niels Justesen, Ruben Rodriguez Torrado, Philip Bontrager, Ahmed Khalifa, Julian Togelius, Sebastian Risi

Jakob Foerster on Multi-Agent learning, Cooperation vs Competition, Emergent Communication, Zero-shot coordination, Opponent Shaping, agents for Hanabi and Prisoner's Dilemma, and more.  

Jakob Foerster is an Associate Professor at University of Oxford.  

Featured References  

Learning with Opponent-Learning Awareness 
Jakob N. Foerster, Richard Y. Chen, Maruan Al-Shedivat, Shimon Whiteson, Pieter Abbeel, Igor Mordatch  

Model-Free Opponent Shaping 
Chris Lu, Timon Willi, Christian Schroeder de Witt, Jakob Foerster  

Off-Belief Learning 
Hengyuan Hu, Adam Lerer, Brandon Cui, David Wu, Luis Pineda, Noam Brown, Jakob Foerster  

Learning to Communicate with Deep Multi-Agent Reinforcement Learning 
Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, Shimon Whiteson  

Adversarial Cheap Talk 
Chris Lu, Timon Willi, Alistair Letcher, Jakob Foerster  

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning 
Yat Long Lo, Christian Schroeder de Witt, Samuel Sokota, Jakob Nicolaus Foerster, Shimon Whiteson  

Additional References  

• Lectures by Jakob on youtube 

Danijar Hafner on the DreamerV3 agent and world models, the Director agent and heirarchical RL,  realtime RL on robots with DayDreamer, and his framework for unsupervised agent design!

Danijar Hafner is a PhD candidate at the University of Toronto with Jimmy Ba, a visiting student at UC Berkeley with Pieter Abbeel, and an intern at DeepMind.  He has been our guest before back on episode 11.  

Featured References   

Mastering Diverse Domains through World Models [ blog ] DreaverV3 

Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap  

DayDreamer: World Models for Physical Robot Learning [ blog ] 
Philipp Wu, Alejandro Escontrela, Danijar Hafner, Ken Goldberg, Pieter Abbeel 

Deep Hierarchical Planning from Pixels [ blog ] 
Danijar Hafner, Kuang-Huei Lee, Ian Fischer, Pieter Abbeel   

Action and Perception as Divergence Minimization [ blog ] 
Danijar Hafner, Pedro A. Ortega, Jimmy Ba, Thomas Parr, Karl Friston, Nicolas Heess 

Additional References  

• Mastering Atari with Discrete World Models [ blog ] DreaverV2 ; Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba  
• Dream to Control: Learning Behaviors by Latent Imagination [ blog ] Dreamer ; Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi  
• Planning to Explore via Self-Supervised World Models ; Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis, Pieter Abbeel, Danijar Hafner, Deepak Pathak  

AI Generating Algos, Learning to play Minecraft with Video PreTraining (VPT), Go-Explore for hard exploration, POET and Open Endedness, AI-GAs and ChatGPT, AGI predictions, and lots more!  

Professor Jeff Clune is Associate Professor of Computer Science at University of British Columbia, a Canada CIFAR AI Chair and Faculty Member at Vector Institute, and Senior Research Advisor at DeepMind.  

Featured References 

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos [ Blog Post ]
Bowen Baker, Ilge Akkaya, Peter Zhokhov, Joost Huizinga, Jie Tang, Adrien Ecoffet, Brandon Houghton, Raul Sampedro, Jeff Clune 

Robots that can adapt like animals
Antoine Cully, Jeff Clune, Danesh Tarapore, Jean-Baptiste Mouret 

Illuminating search spaces by mapping elites
Jean-Baptiste Mouret, Jeff Clune 

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Rui Wang, Joel Lehman, Aditya Rawal, Jiale Zhi, Yulun Li, Jeff Clune, Kenneth O. Stanley 

Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Rui Wang, Joel Lehman, Jeff Clune, Kenneth O. Stanley 

First return, then explore
Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, Jeff Clune

Hear about why OpenAI cites her work in RLHF and dialog models, approaches to rewards in RLHF, ChatGPT, Industry vs Academia, PsiPhi-Learning, AGI and more! 

Dr Natasha Jaques is a Senior Research Scientist at Google Brain.

Featured References

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Natasha Jaques, Asma Ghandeharioun, Judy Hanwen Shen, Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, Rosalind Picard 

Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
Natasha Jaques, Shixiang Gu, Dzmitry Bahdanau, José Miguel Hernández-Lobato, Richard E. Turner, Douglas Eck 

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Angelos Filos, Clare Lyle, Yarin Gal, Sergey Levine, Natasha Jaques, Gregory Farquhar 

Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience
Marwa Abdulhai, Natasha Jaques, Sergey Levine 

Additional References  

• Fine-Tuning Language Models from Human Preferences, Daniel M. Ziegler et al 2019  
• Learning to summarize from human feedback, Nisan Stiennon et al 2020  
• Training language models to follow instructions with human feedback, Long Ouyang et al 2022  

Jacob Beck and Risto Vuorio on their recent Survey of Meta-Reinforcement Learning.  Jacob and Risto are Ph.D. students at Whiteson Research Lab at University of Oxford.   

Featured Reference   

A Survey of Meta-Reinforcement Learning
Jacob Beck, Risto Vuorio, Evan Zheran Liu, Zheng Xiong, Luisa Zintgraf, Chelsea Finn, Shimon Whiteson   

Additional References  

• VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning, Luisa Zintgraf et al  
• Mastering Diverse Domains through World Models (Dreamerv3), Hafner et al    
• Unsupervised Meta-Learning for Reinforcement Learning (MAML), Gupta et al  
• Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices (DREAM), Liu et al  
• RL2: Fast Reinforcement Learning via Slow Reinforcement Learning, Duan et al  
• Learning to reinforcement learn, Wang et al  

John Schulman is a cofounder of OpenAI, and currently a researcher and engineer at OpenAI.

Featured References

WebGPT: Browser-assisted question-answering with human feedback
Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, John Schulman

Training language models to follow instructions with human feedback
Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, Ryan Lowe

Additional References

• Our approach to alignment research, OpenAI 2022
• Training Verifiers to Solve Math Word Problems, Cobbe et al 2021
• UC Berkeley Deep RL Bootcamp Lecture 6: Nuts and Bolts of Deep RL Experimentation, John Schulman 2017
• Proximal Policy Optimization Algorithms, Schulman 2017
• Optimizing Expectations: From Deep Reinforcement Learning to Stochastic Computation Graphs, Schulman 2016

Sven Mika is the Reinforcement Learning Team Lead at Anyscale, and lead committer of RLlib. He holds a PhD in biomathematics, bioinformatics, and computational biology from Witten/Herdecke University. 

Featured References

RLlib Documentation: RLlib: Industry-Grade Reinforcement Learning

Ray: Documentation

RLlib: Abstractions for Distributed Reinforcement Learning
Eric Liang, Richard Liaw, Philipp Moritz, Robert Nishihara, Roy Fox, Ken Goldberg, Joseph E. Gonzalez, Michael I. Jordan, Ion Stoica

Episode sponsor: Anyscale

Ray Summit 2022 is coming to San Francisco on August 23-24.
Hear how teams at Dow, Verizon, Riot Games, and more are solving their RL challenges with Ray's RLlib.

Register at raysummit.org and use code RAYSUMMIT22RL for a further 25% off the already reduced prices.

Karol Hausman is a Senior Research Scientist at Google Brain and an Adjunct Professor at Stanford working on robotics and machine learning. Karol is interested in enabling robots to acquire general-purpose skills with minimal supervision in real-world environments.

Fei Xia is a Research Scientist with Google Research. Fei Xia is mostly interested in robot learning in complex and unstructured environments. Previously he has been approaching this problem by learning in realistic and scalable simulation environments (GibsonEnv, iGibson). Most recently, he has been exploring using foundation models for those challenges.

Featured References

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances [ website ]
Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Daniel Ho, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Eric Jang, Rosario Jauregui Ruano, Kyle Jeffrey, Sally Jesmonth, Nikhil J Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Kuang-Huei Lee, Sergey Levine, Yao Lu, Linda Luu, Carolina Parada, Peter Pastor, Jornell Quiambao, Kanishka Rao, Jarek Rettinghouse, Diego Reyes, Pierre Sermanet, Nicolas Sievers, Clayton Tan, Alexander Toshev, Vincent Vanhoucke, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Mengyuan Yan

Inner Monologue: Embodied Reasoning through Planning with Language Models
Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, Pierre Sermanet, Noah Brown, Tomas Jackson, Linda Luu, Sergey Levine, Karol Hausman, Brian Ichter

Additional References

• Large-scale simulation for embodied perception and robot learning, Xia 2021
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation, Kalashnikov et al 2018
• MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale, Kalashnikov et al 2021
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation, Xia et al 2020
• Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills, Chebotar et al 2021  
• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language, Zeng et al 2022

Episode sponsor: Anyscale

Ray Summit 2022 is coming to San Francisco on August 23-24.
Hear how teams at Dow, Verizon, Riot Games, and more are solving their RL challenges with Ray's RLlib.

Register at raysummit.org and use code RAYSUMMIT22RL for a further 25% off the already reduced prices.

Saikrishna Gottipati is an RL Researcher at AI Redefined, working on RL, MARL, human in the loop learning.

Featured References

Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations
AI Redefined, Sai Krishna Gottipati, Sagar Kurandwad, Clodéric Mars, Gregory Szriftgiser, François Chabot

Do As You Teach: A Multi-Teacher Approach to Self-Play in Deep Reinforcement Learning
Currently under review

Learning to navigate the synthetically accessible chemical space using reinforcement learning
Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Karam J. Thomas, Simon Blackburn, Connor W. Coley, Jian Tang, Sarath Chandar, Yoshua Bengio

Additional References

• Asymmetric self-play for automatic goal discovery in robotic manipulation, 2021 OpenAI et al 
• Continuous Coordination As a Realistic Scenario for Lifelong Learning, 2021 Nekoei et al

Episode sponsor: Anyscale

Ray Summit 2022 is coming to San Francisco on August 23-24.
Hear how teams at Dow, Verizon, Riot Games, and more are solving their RL challenges with Ray's RLlib.

Register at raysummit.org and use code RAYSUMMIT22RL for a further 25% off the already reduced prices.

Aravind Srinivas is back!  He is now a research Scientist at OpenAI.

Featured References

Decision Transformer: Reinforcement Learning via Sequence Modeling
Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch

VideoGPT: Video Generation using VQ-VAE and Transformers
Wilson Yan, Yunzhi Zhang, Pieter Abbeel, Aravind Srinivas

Dr. Rohin Shah is a Research Scientist at DeepMind, and the editor and main contributor of the Alignment Newsletter.

Featured References

The MineRL BASALT Competition on Learning from Human Feedback
Rohin Shah, Cody Wild, Steven H. Wang, Neel Alex, Brandon Houghton, William Guss, Sharada Mohanty, Anssi Kanervisto, Stephanie Milani, Nicholay Topin, Pieter Abbeel, Stuart Russell, Anca Dragan

Preferences Implicit in the State of the World
Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca Dragan

Benefits of Assistance over Reward Learning
Rohin Shah, Pedro Freire, Neel Alex, Rachel Freedman, Dmitrii Krasheninnikov, Lawrence Chan, Michael D Dennis, Pieter Abbeel, Anca Dragan, Stuart Russell

On the Utility of Learning about Humans for Human-AI Coordination
Micah Carroll, Rohin Shah, Mark K. Ho, Thomas L. Griffiths, Sanjit A. Seshia, Pieter Abbeel, Anca Dragan

Evaluating the Robustness of Collaborative Agents
Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, A. D. Dragan, Rohin Shah

Additional References

• AGI Safety Fundamentals, EA Cambridge

Jordan Terry is a PhD candidate at University of Maryland, the maintainer of Gym, the maintainer and creator of PettingZoo and the founder of Swarm Labs.

Featured References

PettingZoo: Gym for Multi-Agent Reinforcement Learning
J. K. Terry, Benjamin Black, Nathaniel Grammel, Mario Jayakumar, Ananth Hari, Ryan Sullivan, Luis Santos, Rodrigo Perez, Caroline Horsch, Clemens Dieffendahl, Niall L. Williams, Yashas Lokesh, Praveen Ravi

PettingZoo on Github

gym on Github

Additional References

• Time Limits in Reinforcement Learning, Pardo et al 2017
• Deep Reinforcement Learning at the Edge of the Statistical Precipice, Agarwal et al 2021

Robert Tjarko Lange is a PhD student working at the Technical University Berlin.

Featured References

Learning not to learn: Nature versus nurture in silico
Lange, R. T., & Sprekeler, H. (2020)

On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning
Vischer, M. A., Lange, R. T., & Sprekeler, H. (2021).

Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions
Lange, R. T., & Faisal, A. (2019).

MLE-Infrastructure on Github


Additional References

• RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning, Duan et al 2016
• Learning to reinforcement learn, Wang et al 2016
• Decision Transformer: Reinforcement Learning via Sequence Modeling, Chen et al 2021

We hear about the idea of PERLS and why its important to talk about.

• Political Economy of Reinforcement Learning (PERLS) Workshop at NeurIPS 2021 on Tues Dec 14th 
• NeurIPS 2021

Amy Zhang is a postdoctoral scholar at UC Berkeley and a research scientist at Facebook AI Research. She will be starting as an assistant professor at UT Austin in Spring 2023. 

Featured References 

Invariant Causal Prediction for Block MDPs 
Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup 

Multi-Task Reinforcement Learning with Context-based Representations 
Shagun Sodhani, Amy Zhang, Joelle Pineau 

MBRL-Lib: A Modular Library for Model-based Reinforcement Learning 
Luis Pineda, Brandon Amos, Amy Zhang, Nathan O. Lambert, Roberto Calandra 

Additional References 

• Amy Zhang - Exploring Context for Better Generalization in Reinforcement Learning @ UCL DARK 
• ICML 2020 Poster session: Invariant Causal Prediction for Block MDPs 
• Clare Lyle - Invariant Prediction for Generalization in Reinforcement Learning @ Simons Institute 

Xianyuan Zhan is currently a research assistant professor at the Institute for AI Industry Research (AIR), Tsinghua University.  He received his Ph.D. degree at Purdue University. Before joining Tsinghua University, Dr. Zhan worked as a researcher at Microsoft Research Asia (MSRA) and a data scientist at JD Technology.  At JD Technology, he led the research that uses offline RL to optimize real-world industrial systems. 

Featured References 

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning
Xianyuan Zhan, Haoran Xu, Yue Zhang, Yusen Huo, Xiangyu Zhu, Honglei Yin, Yu Zheng 

Eugene Vinitsky is a PhD student at UC Berkeley advised by Alexandre Bayen. He has interned at Tesla and Deepmind.  

Featured References 

A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings 
Eugene Vinitsky, Raphael Köster, John P. Agapiou, Edgar Duéñez-Guzmán, Alexander Sasha Vezhnevets, Joel Z. Leibo 

Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL 
Eugene Vinitsky, Nathan Lichtle, Kanaad Parvate, Alexandre Bayen 

Lagrangian Control through Deep-RL: Applications to Bottleneck Decongestion 
Eugene Vinitsky; Kanaad Parvate; Aboudy Kreidieh; Cathy Wu; Alexandre Bayen 2018 

The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games 
Chao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre Bayen, Yi Wu 

Additional References 

• SUMO: Simulation of Urban MObility 

Dr. Jess Whittlestone is a Senior Research Fellow at the Centre for the Study of Existential Risk and the Leverhulme Centre for the Future of Intelligence, both at the University of Cambridge. 

Featured References 

The Societal Implications of Deep Reinforcement Learning 
Jess Whittlestone, Kai Arulkumaran, Matthew Crosby 

Artificial Canaries: Early Warning Signs for Anticipatory and Democratic Governance of AI 
Carla Zoe Cremer, Jess Whittlestone 


Additional References 

• CogX: Cutting Edge: Understanding AI systems for a better AI policy, featuring Jack Clark and Jess Whittlestone 

Dr Aleksandra Faust is a Staff Research Scientist and Reinforcement Learning research team co-founder at Google Brain Research.

Featured References

Reinforcement Learning and Planning for Preference Balancing Tasks 
Faust 2014

Learning Navigation Behaviors End-to-End with AutoRL
Hao-Tien Lewis Chiang, Aleksandra Faust, Marek Fiser, Anthony Francis

Evolving Rewards to Automate Reinforcement Learning 
Aleksandra Faust, Anthony Francis, Dar Mehta 

Evolving Reinforcement Learning Algorithms 

John D Co-Reyes, Yingjie Miao, Daiyi Peng, Esteban Real, Quoc V Le, Sergey Levine, Honglak Lee, Aleksandra Faust 

Adversarial Environment Generation for Learning to Navigate the Web 
Izzeddin Gur, Natasha Jaques, Kevin Malta, Manoj Tiwari, Honglak Lee, Aleksandra Faust 

Additional References 

• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch, Esteban Real, Chen Liang, David R. So, Quoc V. Le 

Sam Ritter is a Research Scientist on the neuroscience team at DeepMind.

Featured References

Unsupervised Predictive Memory in a Goal-Directed Agent (MERLIN)
Greg Wayne, Chia-Chun Hung, David Amos, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwinska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, Timothy Lillicrap

Meta-RL without forgetting:  Been There, Done That: Meta-Learning with Episodic Recall
Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew Botvinick

Meta-Reinforcement Learning with Episodic Recall: An Integrative Theory of Reward-Driven Learning 
Samuel Ritter 2019 

Meta-RL exploration and planning: Rapid Task-Solving in Novel Environments 
Sam Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matt Botvinick, David Raposo 

Synthetic Returns for Long-Term Credit Assignment 
David Raposo, Sam Ritter, Adam Santoro, Greg Wayne, Theophane Weber, Matt Botvinick, Hado van Hasselt, Francis Song 

Additional References 

• Sam Ritter: Meta-Learning to Make Smart Inferences from Small Data , North Star AI 2019 
• The Bitter Lesson, Rich Sutton 2019 

Thomas Krendl Gilbert is a PhD student at UC Berkeley’s Center for Human-Compatible AI, specializing in Machine Ethics and Epistemology. 

Featured References 

Hard Choices in Artificial Intelligence: Addressing Normative Uncertainty through Sociotechnical Commitments 
Roel Dobbe, Thomas Krendl Gilbert, Yonatan Mintz 

Mapping the Political Economy of Reinforcement Learning Systems: The Case of Autonomous Vehicles 
Thomas Krendl Gilbert 

AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks 
McKane Andrus, Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert and Tom Zick 

Additional References 

• Political Economy of Reinforcement Learning Systems (PERLS) 
• The Law and Political Economy (LPE) Project 
• The Societal Implications of Deep Reinforcement Learning, Jess Whittlestone, Kai Arulkumaran, Matthew Crosby 
• Robot Brains Podcast: Yann LeCun explains why Facebook would crumble without AI 

Professor Marc G. Bellemare is a Research Scientist at Google Research (Brain team), An Adjunct Professor at McGill University, and a Canada CIFAR AI Chair. 

Featured References 

The Arcade Learning Environment: An Evaluation Platform for General Agents 
Marc G. Bellemare, Yavar Naddaf, Joel Veness, Michael Bowling 

Human-level control through deep reinforcement learning 
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg & Demis Hassabis 

Autonomous navigation of stratospheric balloons using reinforcement learning 
Marc G. Bellemare, Salvatore Candido, Pablo Samuel Castro, Jun Gong, Marlos C. Machado, Subhodeep Moitra, Sameera S. Ponda & Ziyu Wang 

Additional References 

• CAIDA Talk: A tour of distributional reinforcement learning November 18, 2020 - Marc G. Bellemare 
• Amii AI Seminar Series:  Autonomous nav of stratospheric balloons using RL, Marlos C. Machado 
• UMD RLSS | Marc Bellemare | A History of Reinforcement Learning: Atari to Stratospheric Balloons 
• TalkRL: Marlos C. Machado, Dr. Machado also spoke to us about various aspects of ALE and Project Loon in depth 
• Hyperbolic discounting and learning over multiple horizons, Fedus et al 2019 
• Marc G. Bellemare on Twitter 

Robert Osazuwa Ness is an adjunct professor of computer science at Northeastern University, an ML Research Engineer at Gamalon, and the founder of AltDeep School of AI.  He holds a PhD in statistics.  He studied at Johns Hopkins SAIS and then Purdue University. 

References 

• Altdeep School of AI, Altdeep on Twitch, Substack, Robert Ness 
• Altdeep Causal Generative Machine Learning Minicourse, Free course 
• Robert Osazuwa Ness on Google Scholar 
• Gamalon Inc 
• Causal Reinforcement Learning talks, Elias Bareinboim 
• The Bitter Lesson, Rich Sutton 2019 
• The Need for Biases in Learning Generalizations, Tom Mitchell 1980 
• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics, Kansky et al 2017 

Dr. Marlos C. Machado is a research scientist at DeepMind and an adjunct professor at the University of Alberta. He holds a PhD from the University of Alberta and a MSc and BSc from UFMG, in Brazil. 

Featured References 

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents 
Marlos C. Machado, Marc G. Bellemare, Erik Talvitie, Joel Veness, Matthew J. Hausknecht, Michael Bowling 

Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning [ video ] 
Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, Marc G. Bellemare 

Efficient Exploration in Reinforcement Learning through Time-Based Representations 
Marlos C. Machado 

A Laplacian Framework for Option Discovery in Reinforcement Learning [ video ] 
Marlos C. Machado, Marc G. Bellemare, Michael H. Bowling 

Eigenoption Discovery through the Deep Successor Representation 
Marlos C. Machado, Clemens Rosenbaum, Xiaoxiao Guo, Miao Liu, Gerald Tesauro, Murray Campbell 

Exploration in Reinforcement Learning with Deep Covering Options 
Yuu Jinnai, Jee Won Park, Marlos C. Machado, George Dimitri Konidaris 

Autonomous navigation of stratospheric balloons using reinforcement learning 
Marc G. Bellemare, Salvatore Candido, Pablo Samuel Castro, Jun Gong, Marlos C. Machado, Subhodeep Moitra, Sameera S. Ponda & Ziyu Wang 

Generalization and Regularization in DQN 
Jesse Farebrother, Marlos C. Machado, Michael Bowling 

Additional References 

• Amii AI Seminar Series: Marlos C. Machado - Autonomous navigation of stratospheric balloons using RL 
• State of the Art Control of Atari Games Using Shallow Reinforcement Learning, Liang et al 
• Introspective Agents: Confidence Measures for General Value Functions, Sherstan et al 

Nathan Lambert is a PhD Candidate at UC Berkeley. 

Featured References 

Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning 
Nathan O. Lambert, Albert Wilcox, Howard Zhang, Kristofer S. J. Pister, Roberto Calandra 

Objective Mismatch in Model-based Reinforcement Learning 
Nathan Lambert, Brandon Amos, Omry Yadan, Roberto Calandra 

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning 
Nathan O. Lambert, Daniel S. Drew, Joseph Yaconelli, Roberto Calandra, Sergey Levine, Kristofer S.J. Pister 

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning 
Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra 

Additional References 

• Nathan Lambert's blog 
• Nathan Lambert on Google scholar 

Kai Arulkumaran is a researcher at Araya in Tokyo. 

Featured References 

AlphaStar: An Evolutionary Computation Perspective 
Kai Arulkumaran, Antoine Cully, Julian Togelius 

Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation 
Tianhong Dai, Kai Arulkumaran, Tamara Gerbert, Samyakh Tukra, Feryal Behbahani, Anil Anthony Bharath 

Training Agents using Upside-Down Reinforcement Learning 
Rupesh Kumar Srivastava, Pranav Shyam, Filipe Mutz, Wojciech Jaśkowski, Jürgen Schmidhuber 

Additional References 

• Araya 
• NNAISENSE 
• Kai Arulkumaran on Google Scholar 
• https://github.com/Kaixhin/rlenvs 
• https://github.com/Kaixhin/Atari 
• https://github.com/Kaixhin/Rainbow 
• Tschiatschek, S., Arulkumaran, K., Stühmer, J. & Hofmann, K. (2018). Variational Inference for Data-Efficient Model Learning in POMDPs. arXiv:1805.09281. 
• Arulkumaran, K., Dilokthanakul, N., Shanahan, M. & Bharath, A. A. (2016). Classifying Options for Deep Reinforcement Learning. International Joint Conference on Artificial Intelligence, Deep Reinforcement Learning Workshop. 
• Garnelo, M., Arulkumaran, K. & Shanahan, M. (2016). Towards Deep Symbolic Reinforcement Learning. Annual Conference on Neural Information Processing Systems, Deep Reinforcement Learning Workshop. 
• Arulkumaran, K., Deisenroth, M. P., Brundage, M. & Bharath, A. A. (2017). Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine. 
• Agostinelli, A., Arulkumaran, K., Sarrico, M., Richemond, P. & Bharath, A. A. (2019). Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means. Annual Conference on Neural Information Processing Systems, Workshop on Biological and Artificial Reinforcement Learning. 
• Sarrico, M., Arulkumaran, K., Agostinelli, A., Richemond, P. & Bharath, A. A. (2019). Sample-Efficient Reinforcement Learning with Maximum Entropy Mellowmax Episodic Control. Annual Conference on Neural Information Processing Systems, Workshop on Biological and Artificial Reinforcement Learning. 

Michael Dennis is a PhD student at the Center for Human-Compatible AI at UC Berkeley, supervised by Professor Stuart Russell. 

--Michael Dennis 

Featured References

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design [PAIRED]
Michael Dennis, Natasha Jaques, Eugene Vinitsky, Alexandre Bayen, Stuart Russell, Andrew Critch, Sergey Levine
Videos

Adversarial Policies: Attacking Deep Reinforcement Learning 

Adam Gleave, Michael Dennis, Cody Wild, Neel Kant, Sergey Levine, Stuart Russell
Homepage and Videos

Accumulating Risk Capital Through Investing in Cooperation
Charlotte Roman, Michael Dennis, Andrew Critch, Stuart Russell 

Quantifying Differences in Reward Functions [EPIC]
Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike

Additional References 

• Safe Opponent Exploitation, Sam Ganzfried And Tuomas Sandholm 2015 
• Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning, Natasha Jaques et al 2019 
• Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research, Leibo et al 2019 
• Leveraging Procedural Generation to Benchmark Reinforcement Learning, Karl Cobbe et al 2019 
• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions, Wang et al 2019 
• Consequences of Misaligned AI, Zhuang et al 2020 
• Conservative Agency via Attainable Utility Preservation, Turner et al 2019 

Roman Ring is a Research Engineer at DeepMind. 

Featured References 

Grandmaster level in StarCraft II using multi-agent reinforcement learning 
Vinyals et al, 2019 

Replicating DeepMind StarCraft II Reinforcement Learning Benchmark with Actor-Critic Methods 
Roman Ring, 2018 

Additional References 

• Relational Deep Reinforcement Learning,  Zambaldi et al 2018 
• StarCraft II: A New Challenge for Reinforcement Learning, Vinyals et al 2017 
• Safe and Efficient Off-Policy Reinforcement Learning [Retrace(λ)], Munos et al 2016 
• Sample Efficient Actor-Critic with Experience Replay [ACER], Wang et al 2016 
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures [IMPALA/V-trace], Espeholt et al 2018