Safe Reinforcement Learning Python Packages

safety-gymnasium

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

masa-safe-rl

MASA-Safe-RL: A safe reinforcement library for providing a common interface for different constraints and environments

omnisafe

JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.

safemotions

Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors.

clap-family

Conservative Lapse-Action Planning (CLAP): a variational access-and-dwell framework for safe latent trajectory optimization.

robust-gymnasium

A standard API for robust reinforcement learning and a diverse set of reference environments (formerly Gym).

l2r

Open-source reinforcement learning environment for autonomous racing — featured as a conference paper at ICCV 2021 and as the official challenge tracks at both SL4AD@ICML2022 and AI4AD@IJCAI2022. These are the L2R core libraries.

podworld

2D partially observable dynamic world for RL experiments