<ul><li>Significant advances have been made in developing general-purpose embodied AI in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches.</li><li>Low-level controllers frequently become performance bottlenecks due to repeated failures, which is primarily caused by the absence of an episodic memory system.</li><li>MrSteve (Memory Recall Steve) is a novel low-level controller equipped with Place Event Memory (PEM) that captures what, where, and when information from episodes, addressing the limitations of previous models.</li><li>The proposed Exploration Strategy and Memory-Augmented Task Solving Framework improves task-solving and exploration efficiency compared to existing methods.</li></ul>

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

Discover more