One pages

Jump to bottom

Thakorn Swaengkit edited this page Apr 29, 2023 · 1 revision

RL overview and taxonomy

Model-based vs. Model-free method

Value-based vs. Policy-based method

Monte Carlo

Temporal Difference

Function Approximation and Deep Q-Networks

Policy Gradient

Actor-Critic (AC)

Deep Deterministic Policy Gradient (DDPG)