Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints

Autor:	Kasaura, Kazumi, Miura, Shuwa, Kozuno, Tadashi, Yonetani, Ryo, Hoshino, Kenta, Hosoe, Yohei
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Robotics
Zdroj:	IEEE Robotics and Automation Letters 8(8) (2023) 4449-4456
Druh dokumentu:	Working Paper
DOI:	10.1109/LRA.2023.3284378
Popis:	This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial for ensuring the feasibility and safety of actions in real-world systems. We evaluate existing algorithms and their novel variants across multiple robotics control environments, encompassing multiple action constraint types. Our evaluation provides the first in-depth perspective of the field, revealing surprising insights, including the effectiveness of a straightforward baseline approach. The benchmark problems and associated code utilized in our experiments are made available online at github.com/omron-sinicx/action-constrained-RL-benchmark for further research and development. Comment: 8 pages, 7 figures, accepted to Robotics and Automation Letters
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.08743 Zobrazit plný text záznamu View this record from Arxiv