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

🚀 A fast safe reinforcement learning library in PyTorch

🤖 Elegant implementations of offline safe RL algorithms in PyTorch

🔥 Datasets and env wrappers for offline safe reinforcement learning

PyTorch implementation of Constrained Reinforcement Learning for Soft Actor Critic Algorithm

A Survey Analyzing Generalization in Deep Reinforcement Learning

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning. IROS 2023.

Official Code Repository for the POLICEd-RL Paper: https://www.roboticsproceedings.org/rss20/p104.html

[AAAI 2024 (Oral)] Safety-MuJoCo Environments.

Composable safety-filter and auditability layer for tensor-parallel reinforcement learning. CBF safety filters, watchdog registries, pre-registration artifacts, failure forensics.

Correct-by-synthesis reinforcement learning with temporal logic constraints (CoRL)

SAFIRL: Shielded RL with CBF/MPC on Franka-MuJoCo - reproducible training/evaluation, STL-based verification, benchmarks, Docker/CI.

Official implementation of C-TRPO

Poster about Curriculum Induction for Safe Reinforcement Learning

SafeSABR: risk-calibrated adaptive bitrate streaming over Starlink networks

[ECAI-2025] SPOWL: A JAX-based Safe RL framework that adaptively combines planning and policy learning with dynamic safety thresholds.

Author implementation of DSUP(q) algorithms from the NeurIPS 2024 paper "Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning"

20 RL basics notebooks + 10 advanced projects with Streamlit apps covering RLHF, Offline RL, Multi-Agent RL, Safe RL, World Models, RLAIF, Hierarchical RL, Meta-RL, Drug Discovery RL, and Sim-to-Real transfer

Runtime safety through convex projection

Reinforcement Learning in Real Environments