mlsanityData to 7 Oct 2026

Provably Efficient Multi-Task Reinforcement Learning with Model Transfer

arXiv 2107.08622 ↗First posted 19 Jul 2021cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not necessarily identical MDPs, with a goal of improving their collective performance through inter-player information sharing. We design and analyze an algorithm based on the idea of model transfer, and provide gap-dependent and gap-independent upper and lower bounds that characterize the intrinsic complexity of the problem.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 23 of its 52 references that are in the map. First posted on arXiv 19 Jul 2021.

Builds on

23 of 52 references.

References · 23

  1. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  2. 2017Minimax Regret Bounds for Reinforcement Learningcited by 500
  3. 2018Is Q-learning Provably Efficient?cited by 485
  4. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  5. 2019Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Boundscited by 194
  6. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 189
  7. 2017Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learningcited by 175
  8. 2019A Review of Cooperative Multi-Agent Deep Reinforcement Learningcited by 147
  9. 2020Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decompositioncited by 127
  10. 2015Sample Complexity of Episodic Fixed-Horizon Reinforcement Learningcited by 105
  11. 2019Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPscited by 104
  12. 2018Policy Certificates: Towards Accountable Reinforcement Learningcited by 81
11 more
  1. 2019Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systemscited by 77
  2. 2020Q-learning with Logarithmic Regretcited by 59
  3. 2013Sample Complexity of Multi-task Reinforcement Learningcited by 58
  4. 2021Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrapcited by 48
  5. 2021Near-optimal Representation Learning for Linear Bandits and Linear RLcited by 45
  6. 2019Federated Transfer Reinforcement Learning for Autonomous Drivingcited by 43
  7. 2021Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximationcited by 23
  8. 2019A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learningcited by 18
  9. 2018Coordinated Exploration in Concurrent Reinforcement Learningcited by 17
  10. 2020Multitask Bandit Learning Through Heterogeneous Feedback Aggregationcited by 14
  11. 2019A Model-based Approach for Sample-efficient Multi-task Reinforcement Learningcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 6; 2024: 1; 2025: 3; 2026: 1.

16 papers.

Sort:

By area:

  1. 2021Can Q-Learning be Improved with Advice?cited by 13
  2. 2022On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardnesscited by 7
  3. 2023QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharingcited by 6
  4. 2023Multi-task Representation Learning for Pure Exploration in Linear Banditscited by 6
  5. 2022Thompson Sampling for Robust Transfer in Multi-Task Banditscited by 3
  6. 2022Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processescited by 3
  7. 2023Provably Efficient Offline Reinforcement Learning with Perturbed Data Sourcescited by 3
  8. 2025Provable Zero-Shot Generalization in Offline Reinforcement Learningcited by 3
  9. 2025Reinforcement Learning for Individual Optimal Policy from Heterogeneous Datacited by 3
  10. 2022Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximationcited by 2
  11. 2023Robust Knowledge Transfer in Tiered Reinforcement Learningcited by 1
  12. 2023Scaling Distributed Multi-task Reinforcement Learning with Experience Sharingcited by 1
4 more
  1. 2024Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Taskscited by 1
  2. 2025Towards Understanding the Benefit of Multitask Representation Learning in Decision Processcited by 1
  3. 2023Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processescited by 0
  4. 2026CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learningcited by 0