Wrappers and support for RLBench

描述

此议题没有描述。

贡献者指南

技术栈

python

领域

machine learningai

议题类型

feature

难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。

4

预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。

3-5 days

活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。

stale

清晰度议题是否清楚说明期望改动、验收标准和下一步。

unclear

前置要求

Understanding of reinforcement learningFamiliarity with garage's environment APIKnowledge of RLBench

新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。

20

研究方向

The issue requests adding support for RLBench, a robotic manipulation benchmark. Since the body is empty, the first step is to review garage's existing environment wrappers (e.g., in garage/envs/) and RLBench's API (https://github.com/stepjam/RLBench). Then propose a design for wrapping RLBench tasks as garage environments. Consider contributing a new benchmark set following the pattern of existing ones like DMC. No linked PRs or comments provide additional guidance.