safety-gymnasium
Safe RL Benchmark
A unified benchmark for safe reinforcement learning algorithms and environments.
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
394 stars
9 watching
52 forks
Language: Python
last commit: 6 months ago
Linked from 1 awesome list
constraint-rlconstraint-satisfaction-problemreinforcement-learningsafe-policy-optimizationsafe-reinforcement-learningsafe-reinforcement-learning-environmentssafety-criticalsafety-critical-systems
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
| pku-alignment/omnisafe | A framework designed to accelerate the development of safe reinforcement learning algorithms by providing a modular, high-performance platform for parallel computing and out-of-box toolkits. | 939 |
 rll-research/url_benchmark | A benchmark suite for unsupervised reinforcement learning agents, providing pre-trained models and scripts for testing and fine-tuning agent performance. | 332 |
 alex-petrenko/sample-factory | A high-throughput reinforcement learning library with optimized synchronous and asynchronous implementations of policy gradients. | 828 |
 yg-smile/rl_vvc_dataset | A collection of benchmarks and implementations for testing reinforcement learning-based Volt-VAR control algorithms | 20 |
 jjkke88/rl_toolbox | A collection of reinforcement learning algorithms and tools for training agents in complex environments. | 43 |
 google-research/deep_ope | A set of pre-trained reinforcement learning policies and benchmarking data for offline model selection in reinforcement learning. | 85 |
 securitygames/oef | Provides tools and algorithms for developing reinforcement learning policies in game environments. | 3 |
 matthiasplappert/keras-rl | A Python library implementing state-of-the-art deep reinforcement learning algorithms for Keras and OpenAI Gym environments. | 7 |
 ys-zong/vlguard | Improves safety and helpfulness of large language models by fine-tuning them using safety-critical tasks | 45 |
 rlworkgroup/garage | A toolkit for developing and evaluating reinforcement learning algorithms in a reproducible manner | 1,880 |
 toni-sm/skrl | A modular reinforcement learning library with support for various environments and frameworks | 560 |
 enlite-ai/maze | An RL framework for building and training reinforcement learning models in Python | 265 |
 ucsc-vlaa/vllm-safety-benchmark | A benchmark for evaluating the safety and robustness of vision language models against adversarial attacks. | 67 |
 utiasdsl/safe-control-gym | A set of tools and environments for learning-based control and reinforcement learning in robotics with symbolic safety constraints | 623 |
 sjtu-marl/malib | A framework for parallel population-based reinforcement learning | 497 |