mlsanityData to 14 Oct 2026

Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning

arXiv 2509.20766 ↗First posted 25 Sep 2025cs.RO cs.LGcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Multi-task reinforcement learning (MTRL) offers a promising approach to improve sample efficiency and generalization by training agents across multiple tasks, enabling knowledge sharing between them. However, applying MTRL to robotics remains challenging due to the high cost of collecting diverse task data. To address this, we propose MT-L'evy, a novel exploration strategy that enhances sample efficiency in MTRL environments by combining behavior sharing across tasks with temporally extended exploration inspired by L'evy flight. MT-L'evy leverages policies trained on related tasks to guide exploration towards key states, while dynamically adjusting exploration levels based on task success ratios. This approach enables more efficient state-space coverage, even in complex robotics environments. Empirical results demonstrate that MT-L'evy significantly improves exploration and sample efficiency, supported by quantitative and qualitative analyses. Ablation studies further highlight the contribution of each component, showing that combining behavior sharing with adaptive exploration strategies can significantly improve the practicality of MTRL in robotics applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 30 of its 42 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

30 of 42 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance9 Jul
  2. 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization16 Dec
  3. 2024Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks3 Mar

Other references · 27

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  5. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  6. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  7. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  8. 2018Exploration by Random Network Distillationcited by 993
  9. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  10. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  11. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
  12. 2015Policy Distillationcited by 440
15 more
  1. 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 309
  2. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  3. 2022Multi-Task Learning as a Bargaining Gamecited by 215
  4. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 178
  5. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  6. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 95
  7. 2017Surprise-Based Intrinsic Motivation for Deep Reinforcement Learningcited by 83
  8. 2021Conservative Data Sharing for Multi-Task Offline Reinforcement Learningcited by 64
  9. 2023Multi-Task Reinforcement Learning with Mixture of Orthogonal Expertscited by 49
  10. 2022PaCo: Parameter-Compositional Multi-Task Reinforcement Learningcited by 46
  11. 2020Temporally-Extended ε-Greedy Explorationcited by 29
  12. 2021When should agents explore?cited by 20
  13. 2024Multi-Task Reinforcement Learning for Quadrotorscited by 20
  14. 2023Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routingcited by 8
  15. 2023QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharingcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction
  2. 2026Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards
  3. 2025Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
  4. 2025Multi-Task Reinforcement Learning Enables Parameter Scaling
  5. 2026TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
  6. 2026Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
  7. 2026T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler
  8. 2026Temporal Self-Imitation Learning