mlsanityData to 7 Oct 2026

Sharing Knowledge in Multi-Task Deep Reinforcement Learning

arXiv 2401.09561 ↗First posted 17 Jan 2024cs.LGcited by 42

Not on the map. Why?

Abstract (arXiv)

We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning. We leverage the assumption that learning from different tasks, sharing common properties, is helpful to generalize the knowledge of them resulting in a more effective feature extraction compared to learning a single task. Intuitively, the resulting set of features offers performance benefits when used by Reinforcement Learning algorithms. We prove this by providing theoretical guarantees that highlight the conditions for which is convenient to share representations among tasks, extending the well-known finite-time bounds of Approximate Value-Iteration to the multi-task setting. In addition, we complement our analysis by proposing multi-task extensions of three Reinforcement Learning algorithms that we empirically evaluate on widely used Reinforcement Learning benchmarks showing significant improvements over the single-task counterparts in terms of sample efficiency and performance.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 14 of its 38 references that are in the map. First posted on arXiv 17 Jan 2024.

Builds on

14 of 38 references.

References · 14

  1. 2015Continuous control with deep reinforcement learningcited by 3,279
  2. 2017Hindsight Experience Replaycited by 1,096
  3. 2018DeepMind Control Suitecited by 935
  4. 2016Deep Exploration via Bootstrapped DQNcited by 518
  5. 2015Policy Distillationcited by 414
  6. 2017Distral: Robust Multitask Reinforcement Learningcited by 231
  7. 2015The Benefit of Multitask Representation Learningcited by 194
  8. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 176
  9. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 147
  10. 2018Multi-task Deep Reinforcement Learning with PopArtcited by 138
  11. 2013Sample Complexity of Multi-task Reinforcement Learningcited by 58
  12. 2020MushroomRL: Simplifying Reinforcement Learning Researchcited by 50
2 more
  1. 2014A chain rule for the expected suprema of Gaussian processescited by 13
  2. 2019Compositional Transfer in Hierarchical Reinforcement Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 17; 2025: 19; 2026: 6.

42 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applicationscited by 91
  2. 2025R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPOcited by 52
  3. 2024One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotioncited by 34
  4. 2025Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformercited by 15
  5. 2024Offline Multitask Representation Learning for Reinforcement Learningcited by 14
  6. 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learningcited by 14
  7. 2024AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformerscited by 14
  8. 2024Multi-Task Reinforcement Learning for Quadrotorscited by 12
  9. 2024Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RLcited by 10
  10. 2024Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Banditscited by 6
  11. 2024A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Pointscited by 5
  12. 2024LIMT: Language-Informed Multi-Task Visual World Modelscited by 4
30 more
  1. 2025Trajectory World Models for Heterogeneous Environmentscited by 4
  2. 2025One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planningcited by 3
  3. 2024Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environmentscited by 2
  4. 2024Enabling Energy-Efficient Simultaneous Multi-Task Reinforcement Learning through Spiking Neural Networks with Active Dendrites for Bio-inspired Generalist Agentscited by 2
  5. 2025Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learningcited by 2
  6. 2025Sparsity-Driven Plasticity in Multi-Task Reinforcement Learningcited by 2
  7. 2025Prompt and Parameter Co-Optimization for Large Language Modelscited by 2
  8. 2025Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learningcited by 2
  9. 2025Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systemscited by 2
  10. 2024The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedbackcited by 1
  11. 2024How to Solve Contextual Goal-Oriented Problems with Offline Datasets?cited by 1
  12. 2025Towards Understanding the Benefit of Multitask Representation Learning in Decision Processcited by 1
  13. 2025Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Datacited by 1
  14. 2025Simple Optimizers for Convex Aligned Multi-Objective Optimizationcited by 1
  15. 2024Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulationcited by 0
  16. 2024Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learningcited by 0
  17. 2024Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement Learningcited by 0
  18. 2024Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learningcited by 0
  19. 2025A representational framework for learning and encoding structurally enriched trajectories in complex agent environmentscited by 0
  20. 2025Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processescited by 0
  21. 2025Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systemscited by 0
  22. 2025Efficient Morphology-Aware Policy Transfer to New Embodimentscited by 0
  23. 2025Adaptive Policy Backbone via Shared Networkcited by 0
  24. 2025Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Scholacited by 0
  25. 2026Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agentcited by 0
  26. 2026Evidence of an Emergent "Self" in Continual Robot Learningcited by 0
  27. 2026Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigationcited by 0
  28. 2026Representation Learning Enables Scalable Multitask Deep Reinforcement Learningcited by 0
  29. 2026CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learningcited by 0
  30. 2026DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Taskscited by 0