arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.10550cs.LGcs.AIcs.RO
收藏

记忆、基准与机器人:一种用于通过强化学习解决复杂任务的基准

Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning

AXXX;MIRIAI;ITMO University(ITMO大学)

Egor Cherepanov, Nikita Kachaev, Alexey K. Kovalev, Aleksandr I. Panov

AI总结:

本文提出MIKASA基准,旨在通过强化学习解决复杂任务,包含32个记忆密集型任务,用于评估智能体在桌面机器人操作中的记忆能力。

摘要:

记忆对于使智能体处理具有时间和空间依赖性的复杂任务至关重要。尽管许多强化学习(RL)算法包含记忆,但该领域缺乏一个通用的基准来评估智能体在多样化场景中的记忆能力。这一差距在桌面机器人操作中尤为明显,其中记忆对于解决部分可观察任务和确保鲁棒性能至关重要,但目前却没有标准化的基准。为此,我们引入了MIKASA(Memory-Intensive Skills Assessment Suite for Agents),一种全面的记忆强化学习基准,其三个关键贡献是:(1)我们提出了一种全面的分类框架,用于记忆密集型RL任务;(2)我们收集了MIKASA-Base——一个统一的基准,能够系统评估记忆增强智能体在多样化场景中的能力;(3)我们开发了MIKASA-Robo(pip install mikasa-robo-suite)——一个包含32个精心设计的记忆密集型任务的新基准,用于评估桌面机器人操作中的记忆能力。我们的工作引入了一个统一的框架,以推进记忆RL研究,使更鲁棒的系统能够应用于现实世界。MIKASA可在https://tinyurl.com/membenchrobots上获得。

英文摘要:

Memory is crucial for enabling agents to tackle complex tasks with temporal and spatial dependencies. While many reinforcement learning (RL) algorithms incorporate memory, the field lacks a universal benchmark to assess an agent's memory capabilities across diverse scenarios. This gap is particularly evident in tabletop robotic manipulation, where memory is essential for solving tasks with partial observability and ensuring robust performance, yet no standardized benchmarks exist. To address this, we introduce MIKASA (Memory-Intensive Skills Assessment Suite for Agents), a comprehensive benchmark for memory RL, with three key contributions: (1) we propose a comprehensive classification framework for memory-intensive RL tasks, (2) we collect MIKASA-Base -- a unified benchmark that enables systematic evaluation of memory-enhanced agents across diverse scenarios, and (3) we develop MIKASA-Robo (pip install mikasa-robo-suite) -- a novel benchmark of 32 carefully designed memory-intensive tasks that assess memory capabilities in tabletop robotic manipulation. Our work introduces a unified framework to advance memory RL research, enabling more robust systems for real-world use. MIKASA is available at https://tinyurl.com/membenchrobots.

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。

↑