Learning to Find a Goal

This lecture explores a biologically inspired version of the classic task of Reinforcement Learning, where the instructor discusses the hippocampus, place cells in the rat brain, the Morris Water Maze, modeling a maze task, maze navigation with Actor-Critic, and the implementation of spiking neurons. The lecture concludes with a summary linking TD learning in an actor-critic framework to brain functions and showcasing the possibility of learning in a few trials with well-adapted sensory representation.