Model-based versus Model-free Reinforcement Learning

This lecture explores the difference between model-based and model-free reinforcement learning, focusing on how the agent adapts when the goal changes, the definition of each approach, and the advantages of model-based RL, such as the ability to readapt to reward changes and plan future actions in the 'mind'. The lecture also discusses the implementation of Chess and Go as model-based systems without the need to learn the model.