YannBerthelot

PlaneModel. PlaneModel environment for RL

easygrid. Gym environment of simple microgrid simulation for Reinforcement Learning

TargetGym. TargetGym: Fast Setpoint tracking environments in Jax.

CaptAIn_v2. Python

ProbingEnvironments. Probing environments for unit testing of RL/DeepRL algorithms

Ajax. End-To-End Jax Deep RL agents, including average-reward versions

jaxppo. Python

hackathon_RL_XHEC_2020. Python

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

PymgridExperiments. Research experiments of RL agents on Pymgrid