popgym

The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)

Grid2Op a testbed platform to model sequential decision making in power systems.

Multi-objective Gymnasium environments for reinforcement learning

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

PyTorch implementation of Hierarchical Actor Critic (HAC) for OpenAI gym environments

Collection of Reinforcement Learning / Meta Reinforcement Learning Environments.

A framework to build and solve POMDP problems. Documentation: https://h2r.github.io/pomdp-py/

Clean baseline implementation of PPO using an episodic TransformerXL memory

A framework to design Reinforcement Learning environments that model Active Network Management (ANM) tasks in electricity distribution networks.

Baseline implementation of recurrent PPO using truncated BPTT