GenRL
a Pytorch library for Reinforcement Learning
GenRL is a PyTorch reinforcement learning library centered around reproducible and generalizable algorithm implementations. I am currently integrating various Deep and Classical RL agents such as DQN, VPG and SARSA to GenRL
GenRL aims to aid faster paper reproduction and benchmarking by providing the following main features:
- PyTorch-first: Modular, Extensible and Idiomatic Python
- Unified Trainer and Logging class: code reusability and high-level UI
- Ready-made algorithm implementations: ready-made implementations of popular RL algorithms.
- Faster Benchmarking: automated hyperparameter tuning, environment implementations etc.
By integrating these features into GenRL, we aim to eventually support any new algorithm implementation in less than 100 lines.
This page has been accessed at least
times since the counter was last reset.