mlsanityData to 14 Oct 2026

Language-guided Skill Learning with Temporal Variational Inference

arXiv 2402.16354 ↗First posted 26 Feb 2024cs.LG cs.AI cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. Our results demonstrate that agents equipped with our method are able to discover skills that help accelerate learning and outperform baseline skill learning approaches on new long-horizon tasks in BabyAI, a grid world navigation environment, as well as ALFRED, a household simulation environment.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 40 of its 66 references that are in the map. First posted on arXiv 26 Feb 2024.

Builds on

40 of 66 references.

References · 40

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  7. 2023Mastering Diverse Domains through World Modelscited by 1,253
  8. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  9. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  10. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  11. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  12. 2022A Generalist Agentcited by 808
28 more
  1. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  2. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  3. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  4. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  5. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 244
  6. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 223
  7. 2022Multi-Game Decision Transformerscited by 214
  8. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 203
  9. 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 167
  10. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 166
  11. 2021Episodic Transformer for Vision-and-Language Navigationcited by 156
  12. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  13. 2021Skill Induction and Planning with Latent Languagecited by 99
  14. 2023Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidancecited by 86
  15. 2017Mapping Instructions and Visual Observations to Actions with Reinforcement Learningcited by 81
  16. 2016Learning and Transfer of Modulated Locomotor Controllerscited by 59
  17. 2020Learning Robot Skills with Temporal Variational Inferencecited by 54
  18. 2017Multi-Level Discovery of Deep Optionscited by 51
  19. 2017DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrationscited by 43
  20. 2018Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Informationcited by 41
  21. 2019Variational Temporal Abstractioncited by 38
  22. 2022LISA: Learning Interpretable Skill Abstractions from Languagecited by 30
  23. 2021Learning Transferable Motor Skills with Hierarchical Latent Mixture Policiescited by 26
  24. 2023SPRINT: Scalable Policy Pre-Training via Language Instruction Relabelingcited by 24
  25. 2022Learning Options via Compressioncited by 22
  26. 2022Asking for Knowledge: Training RL Agents to Query External Knowledge Using Languagecited by 10
  27. 2022Meta-Learning Parameterized Skillscited by 7
  28. 2022ASPiRe:Adaptive Skill Priors for Reinforcement Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 2.

11 papers.

  1. 2024EPO: Hierarchical LLM Agents with Environment Preference Optimizationcited by 28
  2. 2024DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedbackcited by 25
  3. 2025STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantizationcited by 13
  4. 2025The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learningcited by 10
  5. 2024Enhancing Agent Learning through World Dynamics Modelingcited by 9
  6. 2026Evolving Programmatic Skill Networkscited by 7
  7. 2025Shared Autonomy for Proximal Teachingcited by 4
  8. 2026PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Modelscited by 2
  9. 2025Data-Efficient Multitask DAggercited by 1
  10. 2025Learning Parameterized Skills from Demonstrationscited by 1
  11. 2025Data Augmentation for Instruction Following Policies via Trajectory Segmentationcited by 0