mlsanityData to 7 Oct 2026

T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler

arXiv 2608.30765 ↗First posted 31 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to solve different tasks by sharing parameters across various tasks. However, these methods are faced with inter-task interference since what parameters should be shared across tasks is not addressed, dramatically reducing learning efficiency. To solve these problems, we propose a novel MTRL framework called Task-Specific feature Selector and Scheduler (T3S), which consists of two components: a feature selector and a task scheduler. Specifically, the feature selectors employ hypernetworks to construct task-specific soft masks, which can be applied by globally shared representation to construct task-specific features. The task scheduler selects tasks for learning through two metrics, where the selection probability is inversely proportional to task progress (e.g., success rate) and task learning speed. Experimental results show that T3S consistently outperforms the state-of-the-art MTRL algorithms on various robotics manipulation tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

25 of 40 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  3. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  4. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  5. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  6. 2016HyperNetworkscited by 1,003
  7. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  8. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  9. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  10. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  11. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
  12. 2015Policy Distillationcited by 414
13 more
  1. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  2. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  3. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
  4. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  5. 2020Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropoutcited by 199
  6. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 176
  7. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 159
  8. 2020Multi-Task Reinforcement Learning with Soft Modularizationcited by 138
  9. 2017Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learningcited by 125
  10. 2020Continual Model-Based Reinforcement Learning with Hypernetworkscited by 41
  11. 2021Recomposing the Reinforcement Learning Building Blocks with Hypernetworkscited by 33
  12. 2020Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learningcited by 29
  13. 2020An Efficient Transfer Learning Framework for Multiagent Reinforcement Learningcited by 11

Built on by

Not cited yet.