TalkRL: The Reinforcement Learning Podcast

Dr Thomas Frost is an emergency physician based in London, UK. He is also in the final stages of completing a PhD at University College London, where he has been looking at offline reinforcement learning applied to healthcare settings.

Featured References

Robust Real-Time Mortality Prediction in the Intensive Care Unit using Temporal Difference Learning
Thomas Frost, Kezhi Li, Steve Harris — ML4H Symposium, PMLR 259, 2025

Insulin4RL: Real-Time Insulin Infusions for Offline Reinforcement Learning
Thomas Frost, Steve Harris — PhysioNet, 2026 (RRID:SCR_007345)

The Hidden Risks of Temporal Resampling in Clinical Reinforcement Learning
Thomas Frost, Hrisheekesh Vaidya, Steve Harris — arXiv preprint, 2026

Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning
Thomas Frost, Steve Harris — arXiv preprint, 2026

Additional References

• The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care — Komorowski et al. 2018
• Off by a beat: the effects of temporal misalignment in reinforcement learning for sepsis treatment — Tang et al. 2026
• Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment — Zhang et al. 2021
• Where do doctors disagree? Characterizing Decision Points for Safe Reinforcement Learning in Choosing Vasopressor Treatment — Brown et al. 2025
• Loss of plasticity in deep continual learning — Dohare et al. 2024

Joseph Modayil is the Founder, President & Research Director of Openmind Research Institute.

Featured References 

Openmind Research Institute 

The Alberta Plan for AI Research 
Richard S. Sutton, Michael Bowling, Patrick M. Pilarski 

Additional References  

• Joseph Modayil on Google Scholar  
• Joseph Modayil Homepage  

Danijar Hafner was a Research Scientist at Google DeepMind until recently.

Featured References   

Training Agents Inside of Scalable World Models [ blog ] 
Danijar Hafner, Wilson Yan, Timothy Lillicrap

One Step Diffusion via Shortcut Models
Kevin Frans, Danijar Hafner, Sergey Levine, 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 Diverse Domains through World Models [ blog ] DreaverV3l Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap   
• 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 
• Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos [ Blog Post ], Baker et al

David Abel is a Senior Research Scientist at DeepMind on the Agency team, and an Honorary Fellow at the University of Edinburgh. His research blends computer science and philosophy, exploring foundational questions about reinforcement learning, definitions, and the nature of agency.  

Featured References  

Plasticity as the Mirror of Empowerment  
David Abel, Michael Bowling, André Barreto, Will Dabney, Shi Dong, Steven Hansen, Anna Harutyunyan, Khimya Khetarpal, Clare Lyle, Razvan Pascanu, Georgios Piliouras, Doina Precup, Jonathan Richens, Mark Rowland, Tom Schaul, Satinder Singh  

A Definition of Continual RL  
David Abel, André Barreto, Benjamin Van Roy, Doina Precup, Hado van Hasselt, Satinder Singh  

Agency is Frame-Dependent  
David Abel, André Barreto, Michael Bowling, Will Dabney, Shi Dong, Steven Hansen, Anna Harutyunyan, Khimya Khetarpal, Clare Lyle, Razvan Pascanu, Georgios Piliouras, Doina Precup, Jonathan Richens, Mark Rowland, Tom Schaul, Satinder Singh  

On the Expressivity of Markov Reward  
David Abel, Will Dabney, Anna Harutyunyan, Mark Ho, Michael Littman, Doina Precup, Satinder Singh — Outstanding Paper Award, NeurIPS 2021  

Additional References  

• Bidirectional Communication Theory — Marko 1973  
• Causality, Feedback and Directed Information — Massey 1990  
• The Big World Hypothesis — Javed et al. 2024  
• Loss of plasticity in deep continual learning — Dohare et al. 2024  
• Three Dogmas of Reinforcement Learning — Abel 2024  
• Explaining dopamine through prediction errors and beyond — Gershman et al. 2024  
• David Abel Google Scholar  
• David Abel personal website  

Recorded at Reinforcement Learning Conference 2025 at University of Alberta, Edmonton Alberta Canada.

Featured References

Lecture on the Oak Architecture, Rich Sutton

Alberta Plan, Rich Sutton with Mike Bowling and Patrick Pilarski

Additional References

• Jacob Beck on Google Scholar 
• Alex Goldie on Google Scholar
• Cornelius Braun on Google Scholar
• Reinforcement Learning Conference

We caught up with the RLC Outstanding Paper award winners for your listening pleasure.

Recorded on location at Reinforcement Learning Conference 2025, at University of Alberta, in Edmonton Alberta Canada in August 2025.

Featured References

Empirical Reinforcement Learning Research
Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions
Ayush Jain, Norio Kosaka, Xinhu Li, Kyung-Min Kim, Erdem Biyik, Joseph J Lim

Applications of Reinforcement Learning
WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies
William Solow, Sandhya Saisubramanian, Alan Fern

Emerging Topics in Reinforcement Learning
Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners
Calarina Muslimani, Kerrick Johnstonbaugh, Suyog Chandramouli, Serena Booth, W. Bradley Knox, Matthew E. Taylor

Scientific Understanding in Reinforcement Learning
Multi-Task Reinforcement Learning Enables Parameter Scaling
Reginald McLean, Evangelos Chatzaroulas, J K Terry, Isaac Woungang, Nariman Farsad, Pablo Samuel Castro

We caught up with the RLC Outstanding Paper award winners for your listening pleasure. 

Recorded on location at Reinforcement Learning Conference 2025, at University of Alberta, in Edmonton Alberta Canada in August 2025.

Featured References 

Scientific Understanding in Reinforcement Learning 
How Should We Meta-Learn Reinforcement Learning Algorithms? 
Alexander David Goldie, Zilin Wang, Jakob Nicolaus Foerster, Shimon Whiteson 

Tooling, Environments, and Evaluation for Reinforcement Learning 
Syllabus: Portable Curricula for Reinforcement Learning Agents 
Ryan Sullivan, Ryan Pégoud, Ameen Ur Rehman, Xinchen Yang, Junyun Huang, Aayush Verma, Nistha Mitra, John P Dickerson 

Resourcefulness in Reinforcement Learning 
PufferLib 2.0: Reinforcement Learning at 1M steps/s 
Joseph Suarez 

Theory of Reinforcement Learning 
Deep Reinforcement Learning with Gradient  Eligibility Traces  
Esraa Elelimy, Brett Daley, Andrew Patterson, Marlos C. Machado, Adam White, Martha White  

Prof Thomas Akam is a Neuroscientist at the Oxford University Department of Experimental Psychology.  He is a Wellcome Career Development Fellow and Associate Professor at the University of Oxford, and leads the Cognitive Circuits research group.

Featured References

Brain Architecture for Adaptive Behaviour
Thomas Akam, RLDM 2025 Tutorial

Additional References

• Thomas Akam on Google Scholar
• pyPhotometry : Open source, Python based, fiber photometry data acquisition 
• pyControl : Open source, Python based, behavioural experiment control.
• Uncertainty-based competition between prefrontal and dorsolateral striatal systems for behavioral control, Nathaniel D Daw, Yael Niv, Peter Dayan, 2005
• Further analysis of the hippocampal amnesic syndrome: 14-year follow-up study of H. M., Milner, B., Corkin, S., & Teuber, H. L., 1968
• Internally generated cell assembly sequences in the rat hippocampus, Pastalkova E, Itskov V, Amarasingham A, Buzsáki G. Science. 2008
• Multi-disciplinary Conference on Reinforcement Learning and Decision 2025

Stefano V. Albrecht was previously Associate Professor at the University of Edinburgh, and is currently serving as Director of AI at startup Deepflow. He is a Program Chair of RLDM 2025 and is co-author of the MIT Press textbook "Multi-Agent Reinforcement Learning: Foundations and Modern Approaches".

Featured References

Multi-Agent Reinforcement Learning: Foundations and Modern Approaches

Stefano V. Albrecht,  Filippos Christianos,  Lukas Schäfer

MIT Press, 2024

RLDM 2025: Reinforcement Learning and Decision Making Conference

Dublin, Ireland

EPyMARL: Extended Python MARL framework

https://github.com/uoe-agents/epymarl

Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks

Georgios Papoudakis and Filippos Christianos and Lukas Schäfer and Stefano V. Albrecht

Professor Satinder Singh of Google DeepMind and U of Michigan is co-founder of RLDM.  Here he narrates the origin story of the Reinforcement Learning and Decision Making meeting (not conference).

Recorded on location at Trinity College Dublin, Ireland during RLDM 2025.

Featured References

RLDM 2025: Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM)
June 11-14, 2025 at Trinity College Dublin, Ireland

Satinder Singh on Google Scholar