Data to 7 Oct 2026

Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning

arXiv 1712.07294 ↗First posted 20 Dec 2017cs.AIcited by 77

Not on the map. Why?

Abstract (arXiv)

Learning policies for complex tasks that require multiple different skills is a major challenge in reinforcement learning (RL). It is also a requirement for its deployment in real-world scenarios. This paper proposes a novel framework for efficient multi-task reinforcement learning. Our framework trains agents to employ hierarchical policies that decide when to use a previously learned policy and when to learn a new skill. This enables agents to continually acquire new skills during different stages of training. Each learned task corresponds to a human language description. Because agents can only access previously learned skills through these descriptions, the agent can always provide a human-interpretable description of its choices. In order to help the agent learn the complex temporal dependencies necessary for the hierarchical policy, we provide it with a stochastic temporal grammar that modulates when to rely on previously learned skills and when to execute new skills. We validate our approach on Minecraft games designed to explicitly test the ability to reuse previously learned skills while simultaneously learning new skills.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 16; 2022: 22; 2023: 18; 2024: 8; 2025: 11; 2026: 1.

77 papers.

Sort:

By area:

2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 226
2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
2024Yell At Your Robot: Improving On-the-Fly from Language Correctionscited by 123
2023Policy Expansion for Bridging Offline-to-Online Reinforcement Learningcited by 103
2021Skill Induction and Planning with Latent Languagecited by 99
2021AndroidEnv: A Reinforcement Learning Platform for Androidcited by 90
2022BITS: Bi-level Imitation for Traffic Simulationcited by 80
2021A Survey on Interpretable Reinforcement Learningcited by 70
2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
2021The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 40

38 more

2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
2023MCU: An Evaluation Framework for Open-Ended Game Agentscited by 33
2022Learning to Execute Actions or Ask Clarification Questionscited by 30
2023Thought Cloning: Learning to Think while Acting by Imitating Human Thinkingcited by 30
2022Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021cited by 23
2023Automated Cyber Defence: A Reviewcited by 19
2021Inherently Explainable Reinforcement Learning in Natural Languagecited by 16
2023Structure in Deep Reinforcement Learning: A Survey and Open Problemscited by 16
2021NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environmentcited by 15
2022Survey on Fair Reinforcement Learning: Theory and Practicecited by 14
2022IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022cited by 14
2023Reinforcement Learning Friendly Vision-Language Model for Minecraftcited by 14
2020Scaling Imitation Learning in Minecraftcited by 12
2021Generalization in Text-based Games via Hierarchical Reinforcement Learningcited by 11
2022Explainability in reinforcement learning: perspective and positioncited by 11
2023SPRING: Studying the Paper and Reasoning to Play Gamescited by 11
2024Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learningcited by 11
2023Learning to Identify Critical States for Reinforcement Learning from Videoscited by 9
2021Multitasking Inhibits Semantic Driftcited by 8
2022A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directionscited by 8
2023Improving Long-Horizon Imitation Through Instruction Predictioncited by 8
2023CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observationscited by 8
2022Transfering Hierarchical Structure with Dual Meta Imitation Learningcited by 7
2022Explainability Via Causal Self-Talkcited by 6
2021Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challengescited by 5
2022Causal Counterfactuals for Improving the Robustness of Reinforcement Learningcited by 5
2023ReProHRL: Towards Multi-Goal Navigation in the Real World using Hierarchical Agentscited by 5
2022SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learningcited by 4
2022There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazescited by 4
2022ProtoX: Explaining a Reinforcement Learning Agent via Prototypingcited by 4
2025Model-Agnostic Policy Explanations with Large Language Modelscited by 4
2022Conditional Visual Servoing for Multi-Step Taskscited by 3
2022A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challengescited by 3
2023Explaining Agent Behavior with Large Language Modelscited by 3
2023Understanding Your Agent: Leveraging Large Language Models for Behavior Explanationcited by 3
2024SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Taskscited by 3
2025Integrating Diffusion-based Multi-task Learning with Online Reinforcement Learning for Robust Quadruped Robot Controlcited by 3
2025Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidancecited by 3

50 most cited of 77 All 77 (JSON)