Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
This work addresses the need for a standardized benchmark for memory-intensive reinforcement learning tasks, particularly in tabletop robotic manipulation, which is crucial for developing more robust systems for real-world use.
The authors tackled the lack of a universal benchmark for assessing an agent's memory capabilities in reinforcement learning, resulting in the introduction of MIKASA, a comprehensive benchmark suite. MIKASA includes 32 memory-intensive tasks for tabletop robotic manipulation, enabling systematic evaluation of memory-enhanced agents.
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.