mlsanityData to 7 Oct 2026

Meta-Learning Parameterized Skills

arXiv 2206.03597 ↗First posted 7 Jun 2022cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks. We propose to leverage off-policy Meta-RL combined with a trajectory-centric smoothness term to learn a set of parameterized skills. Our agent can use these learned skills to construct a three-level hierarchical framework that models a Temporally-extended Parameterized Action Markov Decision Process. We empirically demonstrate that the proposed algorithms enable an agent to solve a set of difficult long-horizon (obstacle-course and robot manipulation) tasks.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 50 of its 69 references that are in the map. First posted on arXiv 7 Jun 2022.

Builds on

50 of 69 references.

References · 50

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  6. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  7. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  8. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  9. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
  10. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  11. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  12. 2016Learning to reinforcement learncited by 369
38 more
  1. 2019Dynamics-Aware Unsupervised Discovery of Skillscited by 308
  2. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 210
  3. 2019DeepMDP: Learning Continuous Latent Space Models for Representation Learningcited by 204
  4. 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 164
  5. 2020PLAS: Latent Action Space for Offline Reinforcement Learningcited by 133
  6. 2020Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skillscited by 120
  7. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  8. 2020Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learningcited by 95
  9. 2017Meta Learning Shared Hierarchiescited by 93
  10. 2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 75
  11. 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 68
  12. 2015Deep Reinforcement Learning in Parameterized Action Spacecited by 65
  13. 2021The Option Keyboard: Combining Skills in Reinforcement Learningcited by 65
  14. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 63
  15. 2015Reinforcement Learning with Parameterized Actionscited by 61
  16. 2016Learning and Transfer of Modulated Locomotor Controllerscited by 59
  17. 2021Learning Symbolic Operators for Task and Motion Planningcited by 57
  18. 2018Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Spacecited by 54
  19. 2019Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Spacecited by 53
  20. 2018Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddingscited by 52
  21. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  22. 2019Continuous Meta-Learning without Taskscited by 50
  23. 2022Predicate Invention for Bilevel Planningcited by 49
  24. 2019Efficient Bimanual Manipulation Using Learned Task Schemascited by 44
  25. 2020Continuous-Discrete Reinforcement Learning for Hybrid Control in Roboticscited by 42
  26. 2021Learning Markov State Abstractions for Deep Reinforcement Learningcited by 42
  27. 2022Skill-based Meta-Reinforcement Learningcited by 36
  28. 2021HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representationcited by 33
  29. 2019Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitivescited by 30
  30. 2020Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learningcited by 30
  31. 2020Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learningcited by 29
  32. 2017Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processescited by 28
  33. 2021Learning Transferable Motor Skills with Hierarchical Latent Mixture Policiescited by 26
  34. 2021Block Contextual MDPs for Continual Learningcited by 25
  35. 2019Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spacescited by 22
  36. 2019Composing Task-Agnostic Policies with Deep Reinforcement Learningcited by 20
  37. 2019Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spacescited by 15
  38. 2020Variational Intrinsic Control Revisitedcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 1.

7 papers.

  1. 2024Language-guided Skill Learning with Temporal Variational Inferencecited by 11
  2. 2024Model-based Reinforcement Learning for Parameterized Action Spacescited by 7
  3. 2025Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learningcited by 5
  4. 2024Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulationcited by 3
  5. 2025Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Taskscited by 3
  6. 2025Learning Parameterized Skills from Demonstrationscited by 1
  7. 2026From Noise to Control: Parameterized Diffusion Policiescited by 0