GenRL is a PyTorch-First Reinforcement Learning library centered around reproducible and generalizable algorithm implementations.
reinforcement-learning pytorch deep-q-networks multi-agent-reinforcement-learning code tutorial library research

Reinforcement learning research is moving faster than ever before. In order to keep up with the growing trend and ensure that RL research remains reproducible, GenRL aims to aid faster paper reproduction and benchmarking by providing the following main features:

  • PyTorch-first: Modular, Extensible and Idiomatic Python
  • Tutorials and Documentation: We have over 20 tutorials assuming no knowledge of RL concepts. Basic explanations of algorithms in Bandits, Contextual Bandits, RL, Deep RL, etc.
  • 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.

Currently, the library has implementations of popular classical and Deep RL agents that ready to be deployed. Apart from these, various Bandit algorithms are a part of GenRL. It has various abstraction layers that make the addition of new algorithms easy for the user.

The library aims to add other key research areas like Multi-agent RL, Evolutionary RL and hyperparameter optimization and provide extensive support for distributed training of agents.

Don't forget to tag @SforAiDl , @Het-Shah , @Sharad24 , @ajaysub110 , @sampreet-arthi , @threewisemonkeys-as in your comment, otherwise they may not be notified.

Authors original post
BITS GOA Computer Science Undergrad | AI & Machine Learning Enthusiast | Maven
RL and DL enthusiast | Collaborator at GenRL | Undergrad at BITS Goa
Computer Science student at BITS Pilani, Goa.
Share this project
Similar projects
DQN In Pytorch Livestream Series
I'm doing a series of streams about reinforcement learning (starting from Q learning) focused on showing the work in as much detail as possible (e.g. ...
Deep Q-Network on Space Invaders.
This is a PyTorch implementation of a Deep Q-Network agent trained to play the Atari 2600 game of Space Invaders.
The Autonomous Learning Library
A PyTorch library for building deep reinforcement learning agents.
Ray is a fast and simple framework for building and running distributed applications.
Top collections