CS234: Reinforcement Learning Winter 2025
https://web.stanford.edu/class/cs234/
#HackerNews #CS234 #ReinforcementLearning #Winter2025 #StanfordAI #MachineLearning #Education
🧠 New preprint by Codol et al. (2025): Brain-like #NeuralDynamics for #behavioral control develop through #ReinforcementLearning. They show that only #RL, not #SupervisedLearning, yields neural activity geometries & dynamics matching monkey #MotorCortex recordings. RL-trained #RNNs operate at the edge of #chaos, reproduce adaptive reorganization under #visuomotor rotation, and require realistic limb #biomechanics to achieve brain-like control.
🧠 New paper by Pedamonti et al. (2025, Nature Comm.) shows that the #hippocampus supports multi-task #ReinforcementLearning under partial observability. Mice flexibly inferred hidden task states 🐁, and only models with recurrent memory reproduced behavior, linking #hippocampal dynamics to #POMDP (Partially Observable Multi-Task Reinforcement Learning) inference.
Fig. 1: Ego-allocentric task setup in animals and reinforcement learning agents.
Fig. 4: Hippocampal RL agents with recurrence capture animal behaviour.