TalkRL: Reinforcement Learning Interviews

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 ReferenceBack to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMsArash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, Sara HookerAdditional ReferencesSelf-Rewarding Language Models, Yuan et al 2024 Reinforcement Learning: An Introduction, Sutton and Barto 1992Learning from Delayed Rewards, Chris Watkins 1989Simple 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 Neu

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 2023Data 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 Bell

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 Rep

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 AcademicsJulian Togelius, Georgios N. YannakakisLearning Controllable 3D Level GeneratorsZehua Jiang, Sam Earle, Michael Cerny Green, Julian TogeliusPCGRL: Procedural Content Generation via Reinforcement LearningAhmed Khalifa, Philip Bontrager, Sam Earle, Julian TogeliusIlluminating Generalization in Deep Reinforcement Learning through Procedural Level GenerationNiels 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  Addi

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 ] Dreav

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 

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

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 LearningJacob 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 ReferencesWebGPT: Browser-assisted question-answering with human feedbackReiichiro 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 SchulmanTraining language models to follow instructions with human feedbackLong 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 LoweAdditional 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

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 ReferencesRLlib Documentation: RLlib: Industry-Grade Reinforcement LearningRay: DocumentationRLlib: Abstractions for Distributed Reinforcement LearningEric Liang, Richard Liaw, Philipp Moritz, Robert Nishihara, Roy Fox, Ken Goldberg, Joseph E. Gonzalez, Michael I. Jordan, Ion StoicaEpisode sponsor: AnyscaleRay 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 ReferencesDo 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, Rya

Saikrishna Gottipati is an RL Researcher at AI Redefined, working on RL, MARL, human in the loop learning.Featured ReferencesCogment: Open Source Framework For Distributed Multi-actor Training, Deployment & OperationsAI Redefined, Sai Krishna Gottipati, Sagar Kurandwad, Clodéric Mars, Gregory Szriftgiser, François ChabotDo As You Teach: A Multi-Teacher Approach to Self-Play in Deep Reinforcement LearningCurrently under reviewAdditional 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: AnyscaleRay 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 ReferencesDecision Transformer: Reinforcement Learning via Sequence ModelingLili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor MordatchVideoGPT: Video Generation using VQ-VAE and TransformersWilson 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 ReferencesThe MineRL BASALT Competition on Learning from Human FeedbackRohin 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 DraganPreferences Implicit in the State of the WorldRohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca DraganBenefits 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 RussellOn the Utility of Learning about Humans for Human-AI CoordinationMicah Carroll, Rohin Shah, Mark K. Ho, Thomas L. Griffiths, Sanjit A. Seshia, Pieter Abbeel, Anca DraganEvaluating the Robustness of Collaborative AgentsPaul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, A. D. Dragan, Rohin ShahAd

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 ReferencesPettingZoo: Gym for Multi-Agent Reinforcement LearningJ. 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 RaviPettingZoo on Githubgym on GithubAdditional References Time Limits in Reinforcement Learning, Pardo et al 2017 Deep Reinforcement Learning at the Edge of the Statistical Precipice, Agarwal et al 2021