Abhishek Naik on Continuing RL & Average Reward

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 blogDiscovering 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