• When: Thursdays, 10:00 AM – 12:00 PM Pacific Time
    • (Eastern: 1:00–3:00 PM, UK: 6:00–8:00 PM, Central Europe: 7:00–9:00 PM)
  • Where: Warren Hall, 205 A (UC Berkeley), and Zoom (we share the link over email, or in our Slack)

Spring 2026

Date Topic Presenter Links
2026-02-19 Continuous Thought Machines Luke Darlow paper · slides · YouTube
2026-02-26 Nested Learning: The Illusion of Deep Learning Architectures Ali Behrouz paper · slides · YouTube
2026-03-05 Three Dogmas of Reinforcement Learning David Abel paper · slides · YouTube
2026-03-12 Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light Mani Hamidi paper · slides · YouTube
2026-03-19 Plasticity as the Mirror of Empowerment David Abel paper · slides · YouTube
2026-03-26 The affective gradient hypothesis: an affect-centered account of motivated behavior Amitai Shenhav paper · slides · YouTube
2026-04-02 What neuroscience can tell AI about learning in continuously changing environments Daniel Durstewitz paper · slides · YouTube
2026-04-09 Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics Reece Keller paper · slides · YouTube
2026-04-16 World Modeling with Probabilistic Structure Integration Dan Yamins paper · slides · YouTube
2026-MM-DD What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models Keyon Vafa paper · slides · YouTube
2026-04-30 AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability Fernando Rosas paper · slides · YouTube
2026-05-07 Subjective functions Samuel Gershman paper · slides · YouTube

2025

Date Topic Presenter Links
2026-01-08 RL Debates Wrap Up: Final Debate/Synthesis Hadi Vafaii (moderator) slides · YouTube
2025-12-11 RL Debates 6: Thomas “no reward for you” Ringstrom Thomas Ringstrom paper · slides · YouTube
2025-11-20 The neuron as a direct data-driven controller (Moore et al., 2024) Thelonious Cooper paper · slides · YouTube
2025-11-13 RL Debates 5: Anne “not everything is RL” Collins Anne Collins paper · slides · YouTube
2025-11-06 RL Debates 4: Adam “I literally measured value in the brain” Lowet Adam Lowet paper · slides · YouTube
2025-10-23 RL Debates 3: Niels “you have 1000 brains in your brain” Leadholm Niels Leadholm paper · slides · YouTube
2025-10-17 RL Debates 2: Fritz “learning for the sake of learning” Sommer Fritz Sommer paper · slides · YouTube
2025-10-02 RL Debates 1: Eli “abolish the value function” Sennesh Eli Sennesh paper · slides · YouTube
2025-09-04 Bayesian Online learning in Non-stationary Environments (BONE) by Duran-Martin et al., 2025 Gerardo Duran-Martin paper · slides · YouTube
2025-08-07 Bayesian Online Natural Gradient (BONG) by Jones et al., 2024 Hadi Vafaii, Kaylene Stocking paper · slides · YouTube