修复了元世界基准的不一致问题，提升可复现性与使用体验。
Meta-World+: An Improved, Standardized, RL Benchmark
- 重构元世界基准，统一环境配置与评估流程
- 确保历史算法结果可复现，解决版本差异问题
- 支持用户自定义任务集，适合强化学习研究者
Meta-World 广泛用于评估多任务和元强化学习智能体，要求其同时掌握多种技能。然而自发布以来，存在大量未记录的变更，导致算法间比较不公平。本文旨在澄清文献中的结果歧义，并利用历史版本对多任务和元强化学习基准设计提供洞察。在此过程中，我们发布了 Meta-World 的新开源版本（https://github.com/Farama-Foundation/Metaworld/），具备完整的历史结果可复现性，技术上更易用，且允许用户灵活控制任务集包含的任务。
原文摘要 · Abstract (English)
Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which inhibit a fair comparison of algorithms. This work strives to disambiguate these results from the literature, while also leveraging the past versions of Meta-World to provide insights into multi-task and meta-reinforcement learning benchmark design. Through this process we release a new open-source version of Meta-World (https://github.com/Farama-Foundation/Metaworld/) that has full reproducibility of past results, is more technically ergonomic, and gives users more control over the tasks that are included in a task set.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。