Tools for accelerating safe exploration research.
☆601Apr 2, 2023Updated 3 years ago
Alternatives and similar repositories for safety-gym
Users that are interested in safety-gym are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.☆463Apr 2, 2023Updated 3 years ago
- NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark☆566Dec 4, 2025Updated 6 months ago
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆70Jul 7, 2023Updated 2 years ago
- The repository is for safe reinforcement learning baselines.☆798Mar 13, 2026Updated 3 months ago
- NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms☆413Mar 20, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Safe Multi-Agent MuJoCo benchmark for safe multi-agent reinforcement learning research.☆76Jun 13, 2024Updated 2 years ago
- PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL☆890Apr 29, 2026Updated last month
- Constrained Policy Optimization☆337Jun 7, 2017Updated 9 years ago
- This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.☆633May 18, 2022Updated 4 years ago
- JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.☆1,128Mar 17, 2025Updated last year
- A collection of reference environments for offline reinforcement learning☆1,688Nov 18, 2024Updated last year
- Safe reinforcement learning with stability guarantees☆238Feb 8, 2022Updated 4 years ago
- Library for Model Based RL☆1,064Jul 12, 2024Updated last year
- ☆77Oct 19, 2023Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A set of algorithms and environments to train SafeRL agents, written in TensorFlow2 and OpenAI Gym.☆12Jul 26, 2022Updated 3 years ago
- Implementations of SAILR, PDO, and CSC☆31Jul 15, 2024Updated last year
- Real-World RL Benchmark Suite☆365Aug 11, 2020Updated 5 years ago
- Safe Multi-Agent Isaac Gym benchmark for safe multi-agent reinforcement learning research.☆65Jan 10, 2025Updated last year
- Simple and easily configurable grid world environments for reinforcement learning☆2,462May 30, 2026Updated 3 weeks ago
- Pytorch implementation of "Safe Exploration in Continuous Action Spaces" [Dalal et al.]☆76Jun 2, 2019Updated 7 years ago
- Datasets for data-driven deep reinforcement learning with PyBullet environments☆152Mar 19, 2021Updated 5 years ago
- ☆399Jul 18, 2019Updated 6 years ago
- A toolkit for reproducible reinforcement learning research.☆2,108May 4, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,549Mar 30, 2026Updated 2 months ago
- Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments☆1,167Mar 27, 2026Updated 2 months ago
- Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"☆553Nov 22, 2022Updated 3 years ago
- Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official imp…☆1,427Nov 29, 2023Updated 2 years ago
- Reinforcement Learning in PyTorch☆2,280Jan 4, 2021Updated 5 years ago
- Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning☆1,838Updated this week
- Implementation of PPO Lagrangian in PyTorch☆56Aug 29, 2022Updated 3 years ago
- Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method☆65Mar 24, 2023Updated 3 years ago
- Safe Reinforcement Learning in Constrained Markov Decision Processes☆62Jul 21, 2020Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"☆475Jul 6, 2023Updated 2 years ago
- Unofficial Pytorch code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"☆197Dec 8, 2022Updated 3 years ago
- Official implementation of the paper: Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate☆25Dec 4, 2023Updated 2 years ago
- Author's PyTorch implementation of BCQ for continuous and discrete actions☆664Apr 6, 2021Updated 5 years ago
- Code for the paper "WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning"☆67Aug 3, 2023Updated 2 years ago
- Massively parallel rigidbody physics simulation on accelerator hardware.☆3,197May 18, 2026Updated last month
- 🤖 Elegant implementations of offline safe RL algorithms in PyTorch☆244Sep 13, 2024Updated last year