Safe Multi-Objective MuJoCo
收藏arXiv2025-09-30 收录
下载链接：
https://github.com/SafeRL-Lab/Safe-Multi-Objective-MuJoCo
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是一个专为在MuJoCo框架内严格审查算法而设计的基准测试，涵盖了包括安全多目标半猎豹、安全多目标跳跃者等多种环境。该基准测试不仅包含了详尽的环境设置，还用于评估提出的算法在具有挑战性的安全多目标强化学习任务中的有效性。任务内容聚焦于安全多目标强化学习。
This dataset is a benchmark specifically designed for rigorous algorithm evaluation within the MuJoCo framework. It covers various environments including Safe Multi-Objective HalfCheetah, Safe Multi-Objective Hopper and others. This benchmark not only includes detailed environment configurations, but also serves to evaluate the effectiveness of proposed algorithms in challenging safe multi-objective reinforcement learning tasks. The tasks focus on safe multi-objective reinforcement learning.
提供机构：
SafeRL Lab
