mlsanityData to 14 Oct 2026

Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer

arXiv 2606.12890 ↗First posted 11 Jun 2026cs.ROcited by 1

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Reinforcement learning has achieved remarkable success in learning complex control policies, yet its applicability remains limited due to sample inefficiency and poor generalization across tasks. In this work, we propose RepMT-SAC, a framework for multi-task RL that enables efficient knowledge sharing and robust transfer to new tasks. RepMT-SAC uses spectral MDP decomposition to capture transferable dynamics, structuring the value function into a task-agnostic core with a minimal task-specific adjustment. This design allows for strong zero-shot performance on in-distribution tasks and rapid few-shot adaptation to out-of-distribution tasks. We evaluate RepMT-SAC on quadcopter trajectory-following tasks across in-distribution and out-of-distribution contexts, demonstrating that it outperforms baselines by up to 30%.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 17 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

14 of 17 references.

References · 14

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2019Provably Efficient Reinforcement Learning with Linear Function Approximationcited by 520
  4. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  5. 2016Successor Features for Transfer in Reinforcement Learningcited by 340
  6. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 217
  7. 2019Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Boundcited by 201
  8. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 176
  9. 2021Representation Learning for Online and Offline RL in Low-rank MDPscited by 129
  10. 2020An empirical investigation of the challenges of real-world reinforcement learningcited by 77
  11. 2022Making Linear MDPs Practical via Contrastive Representation Learningcited by 52
  12. 2022Spectral Decomposition Representation for Reinforcement Learningcited by 36
2 more
  1. 2022Latent Variable Representation for Reinforcement Learningcited by 15
  2. 2024Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpointcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Teaching a Robot Dog New Tricks: Diverse Quadruped Skills via Combined Reinforcement and Imitation Learning with Adversarial Task Selectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Multi-Task Reinforcement Learning for Quadrotors
  2. 2025Reflection-Based Task Adaptation for Self-Improving VLA
  3. 2026Sustainable Transfer Learning for Adaptive Robot Skills ↗
  4. 2026From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
  5. 2022On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
  6. 2026Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures
  7. 2026NavRL++: A System-Level Framework for Improving Sim-to-Real Transfer in Reinforcement Learning-Based Robot Navigation
  8. 2025Onboard Mission Replanning for Adaptive Cooperative Multi-Robot Systems