Reinforcement Learning III Mind Map

Reinforcement Learning III

Exploration

Greedy Policy Problem

Exploration Function

Modified Q-learning

Generalisation in RL

Direct Utility Estimation

Adaptive Dynamic Programming

TD Learning

Function Approx. & Widrow–Hoff

Policy Search

Parameterized Policy & Softmax

Policy Gradient

Challenges & Solutions

Click on a concept to see details

Select any node in the mind map to display detailed information.