This repo contains self-contained RL implementations including
- Basic Plot Usage
- Basic OpenAI Gym Usage
- Value Iteration
- Policy Iteration
- Monte Carlo Learning
- SARSA
- Q Learning
- DQN
- Proximal Policy Optimization
- Soft Actor-Critic
- Generalized Advantage Estimate
- Augmented Random Search
For those who want to run without git clone, please find the colab notebooks in this Google Drive.
Lecture notes can also be found in this repo. It contains:
- RL applications
- Model-based methods (MDP, Value Iteration, Policy Iteraction, etc)
- Model-free methods (MC, TD, SARSA, Q-learning, etc)
- Policy-based methods (TRPO, PPO, SAC, etc)
- Population-based methods (CEM, CMA-ES, ARS)
- Summary
contact: sungjoon-choi at korea dot ac dot kr