mlsanityData to 7 Oct 2026

SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition

arXiv 2111.08857 ↗First posted 17 Nov 2021cs.LG cs.AI cs.MAcited by 20

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex ObtainDiamond task with sparse rewards. To address the challenge, in this paper, we present SEIHAI, a Sample-efficient Hierarchical AI, that fully takes advantage of the human demonstrations and the task structure. Specifically, we split the task into several sequentially dependent subtasks, and train a suitable agent for each subtask using reinforcement learning and imitation learning. We further design a scheduler to select different agents for different subtasks automatically. SEIHAI takes the first place in the preliminary and final of the NeurIPS-2020 MineRL competition.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 20 of its 32 references that are in the map. First posted on arXiv 17 Nov 2021.

Builds on

20 of 32 references.

Closest ancestors · 2

Same direction, newest first

  1. 2020Scaling Imitation Learning in Minecraft6 Jul
  2. 2018An Algorithmic Perspective on Imitation Learning16 Nov

Other references · 18

  1. 2015Continuous control with deep reinforcement learningcited by 3,279
  2. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  4. 2016Generative Adversarial Imitation Learningcited by 1,576
  5. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  6. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 833
  7. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  8. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 302
  9. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 210
  10. 2021The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 40
  11. 2019Learning Agent Communication under Limited Bandwidth by Message Pruningcited by 31
  12. 2019The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 25
6 more
  1. 2018Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPGcited by 20
  2. 2020Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learningcited by 18
  3. 2019Neighborhood Cognition Consistent Multi-Agent Reinforcement Learningcited by 17
  4. 2020Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraftcited by 15
  5. 2017ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learningcited by 8
  6. 2021Towards robust and domain agnostic reinforcement learning competitionscited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 10; 2024: 5; 2025: 2.

20 papers.

Sort:

By area:

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  2. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  3. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  4. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  5. 2023Octopus: Embodied Vision-Language Programmer from Environmental Feedbackcited by 73
  6. 2023Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraftcited by 60
  7. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  8. 2023Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Predictioncited by 39
  9. 2023TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systemscited by 39
  10. 2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 35
  11. 2021JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learningcited by 28
  12. 2022MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learnedcited by 26
8 more
  1. 2024Odyssey: Empowering Minecraft Agents with Open-World Skillscited by 26
  2. 2024Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigationcited by 24
  3. 2024S-Agents: Self-organizing Agents in Open-ended Environmentscited by 22
  4. 2024ADAM: An Embodied Causal Agent in Open-World Environmentscited by 13
  5. 2022PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learningcited by 11
  6. 2024MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memorycited by 8
  7. 2025An Efficient Open World Environment for Multi-Agent Social Learningcited by 3
  8. 2025NGENT: Next-Generation AI Agents Must Integrate Multi-Domain Abilities to Achieve Artificial General Intelligencecited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2018Hierarchical Imitation and Reinforcement Learning
  2. 2021Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft
  3. 2020Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations
  4. 2021The MineRL BASALT Competition on Learning from Human Feedback
  5. 2020Active Hierarchical Imitation and Reinforcement Learning
  6. 2025Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
  7. 2022A Ranking Game for Imitation Learning
  8. 2021Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning