DeepAI AI Chat
Log In Sign Up

Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks

by   Haoqi Yuan, et al.
Peking University

We study building a multi-task agent in Minecraft. Without human demonstrations, solving long-horizon tasks in this open-ended environment with reinforcement learning (RL) is extremely sample inefficient. To tackle the challenge, we decompose solving Minecraft tasks into learning basic skills and planning over the skills. We propose three types of fine-grained basic skills in Minecraft, and use RL with intrinsic rewards to accomplish basic skills with high success rates. For skill planning, we use Large Language Models to find the relationships between skills and build a skill graph in advance. When the agent is solving a task, our skill search algorithm walks on the skill graph and generates the proper skill plans for the agent. In experiments, our method accomplishes 24 diverse Minecraft tasks, where many tasks require sequentially executing for more than 10 skills. Our method outperforms baselines in most tasks by a large margin. The project's website and code can be found at


page 9

page 16

page 17


Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics

Skill-based reinforcement learning (RL) has emerged as a promising strat...

Skill Transfer via Partially Amortized Hierarchical Planning

To quickly solve new tasks in complex environments, intelligent agents n...

Voyager: An Open-Ended Embodied Agent with Large Language Models

We introduce Voyager, the first LLM-powered embodied lifelong learning a...

Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skills

Efficient and effective exploration in continuous space is a central pro...

Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback

A promising approach to solving challenging long-horizon tasks has been ...

Skill Machines: Temporal Logic Composition in Reinforcement Learning

A major challenge in reinforcement learning is specifying tasks in a man...

Sub-policy Adaptation for Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning is a promising approach to long-hori...

Code Repositories


Reinforcement learning and planning for Minecraft.

view repo