MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory

TL;DR

This paper introduces MrSteve, a low-level controller with episodic memory for Minecraft agents, significantly enhancing task-solving and exploration by addressing memory limitations in hierarchical AI approaches.

Contribution

We propose PEM, a novel episodic memory system for low-level controllers, and an exploration strategy that improves performance in Minecraft agents.

Findings

Enhanced task-solving efficiency

Improved exploration capabilities

Outperforms existing methods

Abstract

Significant advances have been made in developing general-purpose embodied AI in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. While these approaches, which combine high-level planners with low-level controllers, show promise, low-level controllers frequently become performance bottlenecks due to repeated failures. In this paper, we argue that the primary cause of failure in many low-level controllers is the absence of an episodic memory system. To address this, we introduce MrSteve (Memory Recall Steve), a novel low-level controller equipped with Place Event Memory (PEM), a form of episodic memory that captures what, where, and when information from episodes. This directly addresses the main limitation of the popular low-level controller, Steve-1. Unlike previous models that rely on short-term memory, PEM organizes spatial and event-based data, enabling efficient recall and navigation in long-horizon tasks. Additionally, we propose an Exploration Strategy and a Memory-Augmented Task Solving Framework, allowing agents to alternate between exploration and task-solving based on recalled events. Our approach significantly improves task-solving and exploration efficiency compared to existing methods. We will release our code and demos on the project page: https://sites.google.com/view/mr-steve.