Voyager achieves superior lifelong learning in Minecraft by combining an automatic exploration curriculum, a library of executable skills, and iterative LLM prompting with environment feedback, yielding 3.3x more unique items and 15.3x faster milestone unlocks than prior methods while generalizing技能
Juewu-mc: Playing minecraft with sample-efficient hierarchical reinforcement learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 4roles
background 1polarities
background 1representative citing papers
GITM uses LLMs to generate action plans from text knowledge and memory, enabling agents to complete long-horizon Minecraft tasks at much higher success rates than prior RL methods.
DEPS combines LLM-based interactive planning with a trainable goal selector to create a zero-shot multi-task agent that completes 70+ Minecraft tasks and nearly doubles prior performance.
WISE augments Minecraft agents with causal memory graphs and opportunistic scheduling to raise success rates on long-horizon sparse-reward tasks.
citing papers explorer
-
Voyager: An Open-Ended Embodied Agent with Large Language Models
Voyager achieves superior lifelong learning in Minecraft by combining an automatic exploration curriculum, a library of executable skills, and iterative LLM prompting with environment feedback, yielding 3.3x more unique items and 15.3x faster milestone unlocks than prior methods while generalizing技能
-
WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning
WISE augments Minecraft agents with causal memory graphs and opportunistic scheduling to raise success rates on long-horizon sparse-reward tasks.