arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.09815cs.LG
收藏

TeachMyAgent:深度RL中自动课程学习的基准

TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL

Inria(法国国家信息与自动化研究所);Microsoft Research(微软研究院)

Clément Romac, Rémy Portelas, Katja Hofmann, Pierre-Yves Oudeyer

摘要:

训练能够泛化到多个任务的自主智能体是深度强化学习(DRL)研究的一个关键目标。在改进DRL算法本身的同时,自动课程学习(ACL)研究教师算法如何通过使任务选择适应其不断发展的能力来更有效地训练DRL代理。虽然存在多个标准基准来比较DRL代理,但目前还没有ACL算法。因此,比较现有的方法是困难的,因为太多的实验参数不同的纸张。在这项工作中,我们确定了ACL算法面临的几个关键挑战。在此基础上,我们提出了TeachMyAgent(TA),一个基准的当前ACL算法利用程序任务生成。它包括1)使用程序化Box2D双足步行器环境变体的挑战特定单元测试,以及2)结合大多数ACL挑战的新程序化跑酷环境,使其成为全球性能评估的理想选择。然后,我们使用TeachMyAgent进行比较研究的代表性现有的方法,展示了一些ACL算法,不使用专家知识的竞争力。我们还表明,跑酷环境仍然是一个开放的问题。我们开源了我们的环境,所有学习ACL算法(从开源代码中收集或重新实现),并在https://github.com/flowersteam/TeachMyAgent上提供Python包中的DRL学生。

英文摘要:

Training autonomous agents able to generalize to multiple tasks is a key target of Deep Reinforcement Learning (DRL) research. In parallel to improving DRL algorithms themselves, Automatic Curriculum Learning (ACL) study how teacher algorithms can train DRL agents more efficiently by adapting task selection to their evolving abilities. While multiple standard benchmarks exist to compare DRL agents, there is currently no such thing for ACL algorithms. Thus, comparing existing approaches is difficult, as too many experimental parameters differ from paper to paper. In this work, we identify several key challenges faced by ACL algorithms. Based on these, we present TeachMyAgent (TA), a benchmark of current ACL algorithms leveraging procedural task generation. It includes 1) challenge-specific unit-tests using variants of a procedural Box2D bipedal walker environment, and 2) a new procedural Parkour environment combining most ACL challenges, making it ideal for global performance assessment. We then use TeachMyAgent to conduct a comparative study of representative existing approaches, showcasing the competitiveness of some ACL algorithms that do not use expert knowledge. We also show that the Parkour environment remains an open problem. We open-source our environments, all studied ACL algorithms (collected from open-source code or re-implemented), and DRL students in a Python package available at https://github.com/flowersteam/TeachMyAgent.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑