arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.14210cs.LGcs.AIstat.ML
收藏

使用Catalyst进行高效的包围式学习。RL

Sample Efficient Ensemble Learning with Catalyst.RL

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究所);Yandex(Yandex公司);Moscow Institute of Physics and Technology(莫斯科物理技术学院)

Sergey Kolesnikov, Valentin Khrulkov

摘要:

我们介绍了Catalyst.RL,这是一个开源的PyTorch框架,用于可重复和样本高效的强化学习(RL)研究。Catalyst.RL的主要功能包括大规模异步分布式训练,各种RL算法的有效实现和辅助技巧,如n步返回,值分布,双曲线强化学习等。为了证明Catalyst.RL的有效性,我们将其应用于基于物理的强化学习挑战“NeurIPS 2019:学习移动-走动”的目标是建立一个人体肌肉骨骼模型的运动控制器。环境是计算昂贵的,具有高维连续的动作空间,是随机的。我们的团队获得了第二名,利用Catalyst.RL的能力,在短短几个小时的培训时间内训练高质量和样本效率的RL代理。实验的实现是开源的,因此可以复制结果并尝试新的想法。

英文摘要:

We present Catalyst.RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research. Main features of Catalyst.RL include large-scale asynchronous distributed training, efficient implementations of various RL algorithms and auxiliary tricks, such as n-step returns, value distributions, hyperbolic reinforcement learning, etc. To demonstrate the effectiveness of Catalyst.RL, we applied it to a physics-based reinforcement learning challenge "NeurIPS 2019: Learn to Move -- Walk Around" with the objective to build a locomotion controller for a human musculoskeletal model. The environment is computationally expensive, has a high-dimensional continuous action space and is stochastic. Our team took the 2nd place, capitalizing on the ability of Catalyst.RL to train high-quality and sample-efficient RL agents in only a few hours of training time. The implementation along with experiments is open-sourced so results can be reproduced and novel ideas tried out.

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。

↑