Deep & Advanced RL
A 12-module path through deep & advanced rl, in study order from foundations to the frontier.
Modules
- Deep Q-Networks (DQN)
- Experience Replay and Target Networks
- Double and Dueling DQN
- Deep Policy Gradient Methods
- Soft Actor-Critic
- Model-Based Reinforcement Learning
- Planning and Monte-Carlo Tree Search
- AlphaGo and AlphaZero
- Offline Reinforcement Learning
- Imitation and Inverse Reinforcement Learning
- Hierarchical and Multi-Agent RL
- RLHF and Reward Learning Connections