Actor-Critic Methods
Back to Home
01. Introduction
02. Motivation
03. Bias and Variance
04. Two Ways for Estimating Expected Returns
05. Baselines and Critics
06. Policy-based, Value-Based, and Actor-Critic
07. A Basic Actor-Critic Agent
08. A3C: Asynchronous Advantage Actor-Critic, N-step
09. A3C: Asynchronous Advantage Actor-Critic, Parallel Training
10. A3C: Asynchronous Advantage Actor-Critic, Off- vs On-policy
11. A2C: Advantage Actor-Critic
12. A2C Code Walk-through
13. GAE: Generalized Advantage Estimation
14. DDPG: Deep Deterministic Policy Gradient, Continuous Actions
15. DDPG: Deep Deterministic Policy Gradient, Soft Updates
16. DDPG Code Walk-through
17. Summary
Back to Home
04. Two Ways for Estimating Expected Returns
Two Ways For Estimating Expected Returns
M3 L5 04 Two Ways For Estimating Expected Returns V3