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

[Humanoids 2022] Learning Collision-free and Torque-limited Robot Trajectories based on Alternative Safe Behaviors

robust-gymnasium

[ICLR 2025] Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.

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.

clap-family

Conservative Lapse-Action Planning (CLAP): a variational access-and-dwell framework for safe AI optimization. Surf the conservative-lapse field to the best safe basin and dwell there — theorem-backed, pip-installable, with differentiable PyTorch training adapters.

podworld

OpenAI Gym environment emphasizing Partially Observable Dynamic physics-based fast cross-platform 2D world