mlsanityData to 14 Oct 2026

Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

arXiv 2205.14410 ↗First posted 28 May 2022cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously learned tasks. However, determining which source task qualifies as the most appropriate for knowledge extraction, as well as the choice regarding which algorithm components to transfer, represent severe obstacles to its application in reinforcement learning. The goal of this paper is to address these issues with modular multi-source transfer learning techniques. The proposed techniques automatically learn how to extract useful information from source tasks, regardless of the difference in state-action space and reward function. We support our claims with extensive and challenging cross-domain experiments for visual control.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 35 of its 57 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

35 of 57 references.

References · 35

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  5. 2018World Modelscited by 1,513
  6. 2016Progressive Neural Networkscited by 1,361
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  8. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  9. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  10. 2014How transferable are features in deep neural networks?cited by 1,225
  11. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  12. 2020Mastering Atari with Discrete World Modelscited by 1,007
23 more
  1. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
  2. 2019Model-Based Reinforcement Learning for Ataricited by 502
  3. 2015Policy Distillationcited by 440
  4. 2020Planning to Explore via Self-Supervised World Modelscited by 368
  5. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  6. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265
  7. 2017Distral: Robust Multitask Reinforcement Learningcited by 233
  8. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  9. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 178
  10. 2020Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifierscited by 97
  11. 2019Distilling Policy Distillationcited by 84
  12. 2021Visual Adversarial Imitation Learning using Variational Modelscited by 42
  13. 2019Knowledge Flow: Improve Upon Your Teacherscited by 36
  14. 2021Zoo-Tuning: Adaptive Transfer from a Zoo of Modelscited by 35
  15. 2018Decoupling Dynamics and Reward for Transfer Learningcited by 23
  16. 2019MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamicscited by 18
  17. 2018Importance Weighted Transfer of Samples in Reinforcement Learningcited by 16
  18. 2019A Model-based Approach for Sample-efficient Multi-task Reinforcement Learningcited by 12
  19. 2021Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddingscited by 12
  20. 2020Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatchcited by 8
  21. 2021Fractional Transfer Learning for Deep Model-Based Reinforcement Learningcited by 6
  22. 2021Transfer Reinforcement Learning across Homotopy Classescited by 4
  23. 2021On The Transferability of Deep-Q Networkscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 2.

5 papers.

  1. 2022Mastering the Unsupervised Reinforcement Learning Benchmark from Pixelscited by 21
  2. 2022Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuningcited by 9
  3. 2025A Survey of Reinforcement Learning for Optimization in Automationcited by 4
  4. 2025Sparsity-Driven Plasticity in Multi-Task Reinforcement Learningcited by 2
  5. 2024Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Controlcited by 0