Data to 7 Oct 2026

A Deep Hierarchical Approach to Lifelong Learning in Minecraft

arXiv 1604.07255 ↗First posted 25 Apr 2016cs.AI cs.LGcited by 90

Not on the map. Why?

Abstract (arXiv)

We propose a lifelong learning system that has the ability to reuse and transfer knowledge from one task to another while efficiently retaining the previously learned knowledge-base. Knowledge is transferred by learning reusable skills to solve tasks in Minecraft, a popular video game which is an unsolved and high-dimensional lifelong learning problem. These reusable skills, which we refer to as Deep Skill Networks, are then incorporated into our novel Hierarchical Deep Reinforcement Learning Network (H-DRLN) architecture using two techniques: (1) a deep skill array and (2) skill distillation, our novel variation of policy distillation (Rusu et. al. 2015) for learning skills. Skill distillation enables the HDRLN to efficiently retain knowledge and therefore scale in lifelong learning, by accumulating knowledge and encapsulating multiple reusable skills into a single distilled network. The H-DRLN exhibits superior performance and lower learning sample complexity compared to the regular Deep Q Network (Mnih et. al. 2015) in sub-domains of Minecraft.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 23; 2022: 18; 2023: 17; 2024: 14; 2025: 10; 2026: 6.

90 papers.

Sort:

By area:

2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 112
2022Deep Hierarchical Planning from Pixelscited by 96
2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 91
2021AndroidEnv: A Reinforcement Learning Platform for Androidcited by 90
2024Scaling Instructable Agents Across Many Simulated Worldscited by 67
2023SteP: Stacked LLM Policies for Web Actionscited by 66
2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 63
2023Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraftcited by 60
2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57

38 more

2019Deep Reinforcement Learning from Policy-Dependent Human Feedbackcited by 56
2021The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 40
2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 35
2023MCU: An Evaluation Framework for Open-Ended Game Agentscited by 33
2021JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learningcited by 28
2022Building a Subspace of Policies for Scalable Continual Learningcited by 28
2021Discovery of Options via Meta-Learned Subgoalscited by 27
2022MuZero with Self-competition for Rate Control in VP9 Video Compressioncited by 27
2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
2024Odyssey: Empowering Minecraft Agents with Open-World Skillscited by 26
2021Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoningcited by 25
2022Causality-driven Hierarchical Structure Discovery for Reinforcement Learningcited by 23
2022Intelligent problem-solving as integrated hierarchical reinforcement learningcited by 21
2022General Intelligence Requires Rethinking Explorationcited by 20
2021Solving Compositional Reinforcement Learning Problems via Task Reductioncited by 19
2022Reinforcement learning on graphs: A surveycited by 18
2021AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learningcited by 17
2023Embodied Lifelong Learning for Task and Motion Planningcited by 17
2025A Survey of Continual Reinforcement Learningcited by 16
2021CoMPS: Continual Meta Policy Searchcited by 15
2023Reinforcement Learning Friendly Vision-Language Model for Minecraftcited by 14
2020Provable Hierarchical Imitation Learning via EMcited by 10
2021Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learningcited by 9
2023Embodied Active Learning of Relational State Abstractions for Bilevel Planningcited by 8
2023Hieros: Hierarchical Imagination on Structured State Space Sequence World Modelscited by 8
2021Program Synthesis Guided Reinforcement Learning for Partially Observed Environmentscited by 7
2021Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decompositioncited by 6
2023Feature Interaction Aware Automated Data Representation Transformationcited by 6
2025Learning to Ball: Composing Policies for Long-Horizon Basketball Movescited by 6
2021Unlocking the potential of deep learning for marine ecology: overview, applications, and outlookcited by 5
2022Self-Activating Neural Ensembles for Continual Reinforcement Learningcited by 5
2023Robotic Manipulation Datasets for Offline Compositional Reinforcement Learningcited by 5
2025Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learningcited by 5
2025Distinct Computations Emerge From Compositional Curricula in In-Context Learningcited by 5
2021Lifetime policy reuse and the importance of task capacitycited by 4
2025Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systemscited by 4
2021Disentangling Transfer and Interference in Multi-Domain Learningcited by 3

50 most cited of 90 All 90 (JSON)