mlsanityData to 7 Oct 2026

Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation

arXiv 2410.04855 ↗First posted 7 Oct 2024cs.RO cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Learning skills that interact with objects is of major importance for robotic manipulation. These skills can indeed serve as an efficient prior for solving various manipulation tasks. We propose a novel Skill Learning approach that discovers composable behaviors by solving a large and diverse number of autonomously generated tasks. Our method learns skills allowing the robot to consistently and robustly interact with objects in its environment. The discovered behaviors are embedded in primitives which can be composed with Hierarchical Reinforcement Learning to solve unseen manipulation tasks. In particular, we leverage Asymmetric Self-Play to discover behaviors and Multiplicative Compositional Policies to embed them. We compare our method to Skill Learning baselines and find that our skills are more interactive. Furthermore, the learned skills can be used to solve a set of unseen manipulation tasks, in simulation as well as on a real robotic platform.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 42 of its 49 references that are in the map. First posted on arXiv 7 Oct 2024.

Builds on

42 of 49 references.

References · 42

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  4. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  5. 2017Hindsight Experience Replaycited by 1,096
  6. 2018Exploration by Random Network Distillationcited by 966
  7. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  8. 2016The Option-Critic Architecturecited by 433
  9. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 322
  10. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 302
  11. 2016Variational Intrinsic Controlcited by 262
  12. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
30 more
  1. 2020First return, then explorecited by 256
  2. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 207
  3. 2017Teacher-Student Curriculum Learningcited by 197
  4. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  5. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 182
  6. 2019Skew-Fit: State-Covering Self-Supervised Reinforcement Learningcited by 171
  7. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  8. 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 164
  9. 2017Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Playcited by 139
  10. 2018Self-Imitation Learningcited by 135
  11. 2018Variational Option Discovery Algorithmscited by 121
  12. 2020Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skillscited by 120
  13. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 113
  14. 2021Replay-Guided Adversarial Environment Designcited by 108
  15. 2019MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policiescited by 105
  16. 2020Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutionscited by 103
  17. 2018Unsupervised Control Through Non-Parametric Discriminative Rewardscited by 102
  18. 2020Automatic Curriculum Learning through Value Disagreementcited by 86
  19. 2018Learning Montezuma's Revenge from a Single Demonstrationcited by 76
  20. 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 71
  21. 2021The Option Keyboard: Combining Skills in Reinforcement Learningcited by 65
  22. 2017Data-efficient Deep Reinforcement Learning for Dexterous Manipulationcited by 61
  23. 2022Lipschitz-constrained Unsupervised Skill Discoverycited by 60
  24. 2013Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robotscited by 56
  25. 2021panda-gym: Open-source goal-conditioned environments for robotic learningcited by 56
  26. 2023Controllability-Aware Unsupervised Skill Discoverycited by 49
  27. 2018Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learningcited by 23
  28. 2022It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generationcited by 14
  29. 2021Discovering Generalizable Skills via Automated Generation of Diverse Taskscited by 5
  30. 2022Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discoverycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  2. 2024Combinatorial Rising Banditscited by 1
  3. 2026Game-Guided Skill Discovery through Self-Play for Playable Agent Controlcited by 0