mlsanityData to 7 Oct 2026

Reset-Free Lifelong Learning with Skill-Space Planning

arXiv 2012.03548 ↗First posted 7 Dec 2020cs.LG cs.AI cs.ROcited by 38

Not on the map. Why?

Abstract (arXiv)

The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail drastically when environments are non-stationary and interactions are non-episodic. We propose Lifelong Skill Planning (LiSP), an algorithmic framework for non-episodic lifelong RL based on planning in an abstract space of higher-order skills. We learn the skills in an unsupervised manner using intrinsic rewards and plan over the learned skills using a learned dynamics model. Moreover, our framework permits skill discovery even from offline data, thereby reducing the need for excessive real-world interactions. We demonstrate empirically that LiSP successfully enables long-horizon planning and learns agents that can avoid catastrophic failures even in challenging non-stationary and non-episodic environments derived from gridworld and MuJoCo benchmarks.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 11; 2023: 10; 2024: 4; 2025: 5; 2026: 3.

38 papers.

Sort:

By area:

  1. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  2. 2022Online Decision Transformercited by 194
  3. 2022TransDreamer: Reinforcement Learning with Transformer World Modelscited by 143
  4. 2022Skill-based Model-based Reinforcement Learningcited by 50
  5. 2023Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learningcited by 49
  6. 2023Beyond Reward: Offline Preference-guided Policy Optimizationcited by 35
  7. 2021Autonomous Reinforcement Learning: Formalism and Benchmarkingcited by 33
  8. 2021Autonomous Reinforcement Learning via Subgoal Curriculacited by 32
  9. 2022LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulationcited by 32
  10. 2023Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learningcited by 29
  11. 2022Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learningcited by 28
  12. 2022Building a Subspace of Policies for Scalable Continual Learningcited by 28
26 more
  1. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  2. 2024Practice Makes Perfect: Planning to Learn Skill Parameter Policiescited by 22
  3. 2022A State-Distribution Matching Approach to Non-Episodic Reinforcement Learningcited by 21
  4. 2021Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reachingcited by 19
  5. 2022Pretraining in Deep Reinforcement Learning: A Surveycited by 18
  6. 2025A Survey of Continual Reinforcement Learningcited by 16
  7. 2022Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learningcited by 14
  8. 2023FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicingcited by 13
  9. 2023Efficient Planning with Latent Diffusioncited by 11
  10. 2025Evolution and The Knightian Blindspot of Machine Learningcited by 11
  11. 2022Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methodscited by 9
  12. 2023Embodied Active Learning of Relational State Abstractions for Bilevel Planningcited by 8
  13. 2023Predictable MDP Abstraction for Unsupervised Model-Based RLcited by 7
  14. 2024Intelligent Switching for Reset-Free RLcited by 4
  15. 2026UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learningcited by 4
  16. 2023Provable Reset-free Reinforcement Learning by No-Regret Reductioncited by 3
  17. 2023When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learningcited by 3
  18. 2024Reset-free Reinforcement Learning with World Modelscited by 3
  19. 2021A Simple Approach to Continual Learning by Transferring Skill Parameterscited by 2
  20. 2023Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculumcited by 2
  21. 2025MOSAIC: Skill-Centric Manipulation Planning with Physics Simulationcited by 2
  22. 2024Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Taskscited by 0
  23. 2025Meta Policy Switching for Secure UAV Deconfliction in Adversarial Airspacecited by 0
  24. 2025Optimal control of the future via prospective learning with controlcited by 0
  25. 2026DecisionLLM: Large Language Models for Long Sequence Decision Explorationcited by 0
  26. 2026Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoningcited by 0