Deep Reinforcement Learning
Module 3
Off-Policy Methods & Tooling
DDPG, TD3, and SAC for continuous control, plus the Spinning Up toolkit for running, logging, and benchmarking experiments.
Readings
1
Deep Deterministic Policy Gradient (DDPG)
13 min
2
TD3 & Soft Actor-Critic (SAC)
14 min
3
Running, Logging & Benchmarking
10 min
4
Key Papers in Deep RL
15 min
Quizzes
Labs