mlsanityData to 7 Oct 2026

Decoupling Dynamics and Reward for Transfer Learning

arXiv 1804.10689 ↗First posted 27 Apr 2018cs.LG cs.AI stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. We separate learning the task representation, the forward dynamics, the inverse dynamics and the reward function of the domain, and show that this decoupling improves performance within the task, transfers well to changes in dynamics and reward, and can be effectively used for online planning. Empirical results show good performance in both continuous and discrete RL domains.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 4; 2024: 3; 2025: 2; 2026: 4.

23 papers.

Sort:

By area:

  1. 2023For SALE: State-Action Representation Learning for Deep Reinforcement Learningcited by 73
  2. 2021Learning Markov State Abstractions for Deep Reinforcement Learningcited by 42
  3. 2025Towards General-Purpose Model-Free Reinforcement Learningcited by 40
  4. 2021Which Mutual-Information Representation Learning Objectives are Sufficient for Control?cited by 28
  5. 2022INFOrmation Prioritization through EmPOWERment in Visual Model-Based RLcited by 27
  6. 2021Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawingcited by 22
  7. 2023Simplified Temporal Consistency Reinforcement Learningcited by 17
  8. 2022Multi-Agent Policy Transfer via Task Relationship Modelingcited by 14
  9. 2022Reachability-Aware Laplacian Representation in Reinforcement Learningcited by 10
  10. 2023A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learningcited by 9
  11. 2021Fractional Transfer Learning for Deep Model-Based Reinforcement Learningcited by 6
  12. 2021Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularizationcited by 5
11 more
  1. 2022Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learningcited by 5
  2. 2024Task and Domain Adaptive Reinforcement Learning for Robot Controlcited by 2
  3. 2026Debiased Model-based Representations for Sample-efficient Continuous Controlcited by 1
  4. 2022Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representationscited by 0
  5. 2023Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfercited by 0
  6. 2024Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Controlcited by 0
  7. 2024A Pre-Trained Graph-Based Model for Adaptive Sequencing of Educational Documentscited by 0
  8. 2025Goals and the Structure of Experiencecited by 0
  9. 2026Sensitivity Shaping for Latent Modelingcited by 0
  10. 2026NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learningcited by 0
  11. 2026Reward as Observation: Learning Reward-Based Policies for Rapid Adaptationcited by 0