Reinforcement Learning¶
This module covers reinforcement learning fundamentals and robotics applications.
Topics¶
- Fundamentals - MDP, Bellman equations, value functions
- Value-Based Methods - Q-learning, DQN
- Policy Gradient - REINFORCE, PPO, TRPO
- Model-Based RL - Learn dynamics, MPC
- Robot Applications - RL in manipulation and locomotion
Prerequisites¶
- Python programming
- Basic probability and statistics
- Neural networks basics
Libraries¶
- Stable Baselines3: Reliable RL implementations
- RLlib: Scalable RL
- Tianshou: High-performance Python RL
