Lecture
Model-Based Deep RL: Planning and VAST
Description
This lecture introduces model-based reinforcement learning, focusing on planning in the background. It covers the estimation of transition dynamics and reward structure, the use of models for planning, variational state tabulation, decision time planning, and AlphaZero and MuZero algorithms. The instructor emphasizes the efficiency of updating Q- and V-values through value iteration in model-based reinforcement learning.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.