arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.10447cs.LGcs.AIcs.RO
收藏

环境设计在强化学习中的重要性:一个机器人环境的研究

Importance of Environment Design in Reinforcement Learning: A Study of a Robotic Environment

Budapest University of Technology and Economics(布达佩斯技术与经济大学)

Mónika Farsang, Luca Szegletes

摘要:

对特定环境的深入理解在强化学习(RL)中至关重要。为了解决这一问题,本文研究了移动协作机器人助手的决策过程建模的马尔可夫决策过程(MDP)框架。利用非线性贝尔曼最优性方程计算了MDP的最优状态-动作组合。这个方程组可以通过Wolfram Mathematica的计算能力相对容易地求解,其中获得的最佳动作值指向最佳策略。与其他RL算法不同,该方法不近似最优行为,它给出了精确的,显式的解决方案,这为我们的研究提供了坚实的基础。有了这个,我们提供了新的见解来理解RL中的动作选择机制,通过提出各种小的修改,导致不同的最优策略的非常相同的模式。

英文摘要:

An in-depth understanding of the particular environment is crucial in reinforcement learning (RL). To address this challenge, the decision-making process of a mobile collaborative robotic assistant modeled by the Markov decision process (MDP) framework is studied in this paper. The optimal state-action combinations of the MDP are calculated with the non-linear Bellman optimality equations. This system of equations can be solved with relative ease by the computational power of Wolfram Mathematica, where the obtained optimal action-values point to the optimal policy. Unlike other RL algorithms, this methodology does not approximate the optimal behavior, it gives the exact, explicit solution, which provides a strong foundation for our study. With this, we offer new insights into understanding the action selection mechanisms in RL by presenting various small modifications on the very same schema that lead to different optimal policies.

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。

↑