arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1105.1749cs.AIcs.ROcs.SE
收藏

一种用于机器人控制的实时的基于模型的强化学习结构

A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Todd Hester, Michael Quinlan, Peter Stone

摘要:

强化学习(RL)是一种学习决策任务的方法,可以使机器人在线学习和适应他们的情况。对于机器人控制任务实用的RL算法,它必须在非常少的动作中学习,同时连续地实时的【形】采取这些动作。现有的基于模型的强化学习方法在相对较少的动作中学习,但是对于实际的在线学习来说,每个动作之间通常需要太多的时间。在本文中,我们提出了一种新的基于模型的RL并行架构,该架构通过以下方式实时的【形】运行:1)利用基于样本的近似规划方法; 2)并行化动作,模型学习和规划过程,以便动作过程对于典型的机器人控制周期足够快。我们证明,使用这种架构的算法执行几乎以及使用典型的顺序架构的方法时,都是无限的时间,并大大优于这些方法的任务,需要实时的【形】行动,如控制自动驾驶汽车。

英文摘要:

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few actions, while continually taking those actions in real-time. Existing model-based RL methods learn in relatively few actions, but typically take too much time between each action for practical on-line learning. In this paper, we present a novel parallel architecture for model-based RL that runs in real-time by 1) taking advantage of sample-based approximate planning methods and 2) parallelizing the acting, model learning, and planning processes such that the acting process is sufficiently fast for typical robot control cycles. We demonstrate that algorithms using this architecture perform nearly as well as methods using the typical sequential architecture when both are given unlimited time, and greatly out-perform these methods on tasks that require real-time actions such as controlling an autonomous vehicle.

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。

↑