Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- URL: http://arxiv.org/abs/2310.12567v3
- Date: Sun, 06 Oct 2024 15:42:14 GMT
- Title: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- Authors: Jiaming Ji, Borong Zhang, Jiayi Zhou, Xuehai Pan, Weidong Huang, Ruiyang Sun, Yiran Geng, Yifan Zhong, Juntao Dai, Yaodong Yang,
- Abstract summary: We present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios.
We offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms.
- Score: 12.660770759420286
- License:
- Abstract: Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at https://sites.google.com/view/safety-gymnasium.
Related papers
- ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning [48.536695794883826]
We present ActSafe, a novel model-based RL algorithm for safe and efficient exploration.
We show that ActSafe guarantees safety during learning while also obtaining a near-optimal policy in finite time.
In addition, we propose a practical variant of ActSafe that builds on latest model-based RL advancements.
arXiv Detail & Related papers (2024-10-12T10:46:02Z) - Multimodal Situational Safety [73.63981779844916]
We present the first evaluation and analysis of a novel safety challenge termed Multimodal Situational Safety.
For an MLLM to respond safely, whether through language or action, it often needs to assess the safety implications of a language query within its corresponding visual context.
We develop the Multimodal Situational Safety benchmark (MSSBench) to assess the situational safety performance of current MLLMs.
arXiv Detail & Related papers (2024-10-08T16:16:07Z) - Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? [59.96471873997733]
We propose an empirical foundation for developing more meaningful safety metrics and define AI safety in a machine learning research context.
We aim to provide a more rigorous framework for AI safety research, advancing the science of safety evaluations and clarifying the path towards measurable progress.
arXiv Detail & Related papers (2024-07-31T17:59:24Z) - Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning [57.84059344739159]
"Shielding" is a popular technique to enforce safety inReinforcement Learning (RL)
We propose a new permissibility-based framework to deal with safety and shield construction.
arXiv Detail & Related papers (2024-05-29T18:00:21Z) - The Art of Defending: A Systematic Evaluation and Analysis of LLM
Defense Strategies on Safety and Over-Defensiveness [56.174255970895466]
Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications.
This paper presents Safety and Over-Defensiveness Evaluation (SODE) benchmark.
arXiv Detail & Related papers (2023-12-30T17:37:06Z) - Safe Reinforcement Learning in a Simulated Robotic Arm [0.0]
Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies.
In this paper, we extend the applicability of safe RL algorithms by creating a customized environment with Panda robotic arm.
arXiv Detail & Related papers (2023-11-28T19:22:16Z) - OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning
Research [3.0536277689386453]
We introduce a foundational framework designed to expedite SafeRL research endeavors.
Our framework encompasses an array of algorithms spanning different RL domains and places heavy emphasis on safety elements.
arXiv Detail & Related papers (2023-05-16T09:22:14Z) - Evaluating Model-free Reinforcement Learning toward Safety-critical
Tasks [70.76757529955577]
This paper revisits prior work in this scope from the perspective of state-wise safe RL.
We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection.
To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
arXiv Detail & Related papers (2022-12-12T06:30:17Z) - Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and
Generalization Guarantees [7.6347172725540995]
Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world.
We propose Sim-to-Lab-to-Real to bridge the reality gap with a probabilistically guaranteed safety-aware policy distribution.
arXiv Detail & Related papers (2022-01-20T18:41:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.