This is a playground to implement Reinforcement Algorithms for personal interest.
# for cuda 12.1
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
# gym
conda install -c conda-forge gym
conda install -c conda-forge box2d-py
pip install pygame
- PolicyGradient
- QLearning
- DQN
- A3C (WIP)
- PPO
A class, GymTrainer, warps the gym simulation environment to train a given agent.
It accepts an agent implemented based on the BaseAgent.
This class defines the basic RL agent behaviors and abstract functions to be implemented for different RL algorithms.