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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cherepanov, Egor, Kachaev, Nikita, Kovalev, Alexey K., Panov, Aleksandr I.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915833395019776
author Cherepanov, Egor
Kachaev, Nikita
Kovalev, Alexey K.
Panov, Aleksandr I.
author_facet Cherepanov, Egor
Kachaev, Nikita
Kovalev, Alexey K.
Panov, Aleksandr I.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10550
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
Cherepanov, Egor
Kachaev, Nikita
Kovalev, Alexey K.
Panov, Aleksandr I.
Machine Learning
Artificial Intelligence
Robotics
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.
title Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2502.10550