| 0 |
Prerequisites |
Probability, Linear Algebra, Calculus, Python, ML & DL basics, Markov Chains |
| 1 |
Fundamentals |
MDPs, Bellman equations, DP, Monte Carlo, TD |
| 2 |
Value-Based Methods |
SARSA, Q-Learning, exploration, function approximation |
| 3 |
Policy-Based Methods |
Policy Gradients, REINFORCE, Actor-Critic |
| 4 |
Deep RL |
DQN, DDQN, Dueling DQN, DDPG, TD3, PPO, SAC |
| 5 |
Advanced Topics |
Model-Based, Hierarchical, Multi-Agent, Meta-RL, Offline RL, RLHF |
| 6 |
SOTA RL & Research Trends |
GRPO, DPO, DreamerV3, Decision Transformer, GFlowNets, Diffusion Policies |
| 7 |
Applications |
Robotics, Games, Recommenders, Finance, Code Agents |