FOR.ai Reinforcement Learning Codebase
Modular codebase for reinforcement learning models training, testing and visualization.
- Agents: DQN, Vanilla Policy Gradient, DDPG, PPO
- Model-free asynchronous training (
- Memory replay: Simple, Proportional Prioritized Experience Replay
Example for recorded envrionment on various RL agents.
You need to install the following for your system:
- OpenAI Gym
- OpenAI Atari
- OpenAI ProcGen
- Additional python packages
pip install -r ../requirements.txt
# start training python train.py --sys ... --hparams ... --output_dir ... # run tensorboard tensorboard --logdir ... # test agnet python train.py --sys ... --hparams ... --output_dir ... --test_only --render
hparams: Which hparams to use, defined under rl/hparams
sys: Which system environment to use.
env: Which RL environment to use.
output_dir: The directory for model checkpoints and TensorBoard summary.
train_steps:, Number of steps to train the agent.
test_episodes: Number of episodes to test the agent.
eval_episodes: Number of episodes to evaluate the agent.
test_only: Test agent without training.
copies: Number of independent training/testing runs to do.
render: Render game play.
record_video: Record game play.
num_workers, number of workers.
More detailed documentation can be found here.
We'd love to accept your contributions to this project. Please feel free to open an issue, or submit a pull request as necessary. Contact us email@example.com for potential collaborations and joining FOR.ai.