arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.03275cs.ROcs.AI
收藏

机器人乒乓球中的样本高效强化学习

Sample-efficient Reinforcement Learning in Robotic Table Tennis

University of Tuebingen(图宾根大学)

Jonas Tebbe, Lukas Krauch, Yapeng Gao, Andreas Zell

AI总结:

本文提出一种样本高效的强化学习算法,通过单步环境和Actor-Critic确定性策略梯度加速学习,使乒乓球机器人在无预训练下不到200回合即可实现精准回球。

摘要:

强化学习(RL)在各类计算机游戏和仿真中近期取得了令人瞩目的成就。这些成功大多基于智能体可从中学习的大量回合。然而,在典型的机器人应用中,可行尝试的次数非常有限。本文提出了一种样本高效的RL算法,并应用于乒乓球机器人的实例中。在乒乓球运动中,每次击球都不同,其落点、速度和旋转各异。因此,必须在高维连续状态空间中寻找准确的回球策略。为使在少量试验中学习成为可能,该方法被嵌入到我们的机器人系统中。这样我们就能使用单步环境。状态空间取决于击球时的球的状态(位置、速度、旋转),而动作是击球时的球拍状态(朝向、速度)。我们开发了一种基于Actor-Critic的确定性策略梯度算法以加速学习。我们的方法在仿真和真实机器人的多种挑战性场景中均表现优异。在无预训练的情况下,仅需不到200个回合的训练即可获得准确结果。展示我们实验的视频可在https://youtu.be/uRAtdoL6Wpw查看。

英文摘要:

Reinforcement learning (RL) has achieved some impressive recent successes in various computer games and simulations. Most of these successes are based on having large numbers of episodes from which the agent can learn. In typical robotic applications, however, the number of feasible attempts is very limited. In this paper we present a sample-efficient RL algorithm applied to the example of a table tennis robot. In table tennis every stroke is different, with varying placement, speed and spin. An accurate return therefore has to be found depending on a high-dimensional continuous state space. To make learning in few trials possible the method is embedded into our robot system. In this way we can use a one-step environment. The state space depends on the ball at hitting time (position, velocity, spin) and the action is the racket state (orientation, velocity) at hitting. An actor-critic based deterministic policy gradient algorithm was developed for accelerated learning. Our approach performs competitively both in a simulation and on the real robot in a number of challenging scenarios. Accurate results are obtained without pre-training in under $200$ episodes of training. The video presenting our experiments is available at https://youtu.be/uRAtdoL6Wpw.

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。

↑