mlsanityData to 7 Oct 2026

Combined Reinforcement Learning via Abstract Representations

arXiv 1809.04506 ↗First posted 12 Sep 2018cs.LG cs.AI stat.MLcited by 37

Not on the map. Why?

Abstract (arXiv)

In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this paper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We show that the modularity brought by this approach leads to good generalization while being computationally efficient, with planning happening in a smaller latent state space. In addition, this approach recovers a sufficient low-dimensional representation of the environment, which opens up new strategies for interpretable AI, exploration and transfer learning.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 10; 2023: 3; 2024: 2; 2025: 5; 2026: 1.

37 papers.

Sort:

By area:

  1. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  2. 2021A Survey on Interpretable Reinforcement Learningcited by 70
  3. 2024Bridging State and History Representations: Understanding Self-Predictive RLcited by 52
  4. 2021Towards Robust Bisimulation Metric Learningcited by 49
  5. 2021MICo: Improved representations via sampling-based state similarity for Markov decision processescited by 43
  6. 2021Return-Based Contrastive Representation Learning for Reinforcement Learningcited by 36
  7. 2021Proper Value Equivalencecited by 33
  8. 2022Factored Adaptation for Non-Stationary Reinforcement Learningcited by 30
  9. 2022Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learningcited by 26
  10. 2022Investigating the Properties of Neural Network Representations in Reinforcement Learningcited by 24
  11. 2021Learning First-Order Representations for Planning from Black-Box States: New Resultscited by 23
  12. 2021Domain Adversarial Reinforcement Learningcited by 19
25 more
  1. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  2. 2021Reasoning-Modulated Representationscited by 13
  3. 2025Interpretable Machine Learning in Physics: A Reviewcited by 11
  4. 2021Combining Planning and Learning of Behavior Trees for Robotic Assemblycited by 9
  5. 2021Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spacescited by 9
  6. 2025Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloningcited by 9
  7. 2023Predictive auxiliary objectives in deep RL mimic learning in the braincited by 7
  8. 2021Policy Gradients Incorporating the Futurecited by 6
  9. 2022Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learningcited by 6
  10. 2021Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularizationcited by 5
  11. 2023Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfindingcited by 5
  12. 2022Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Taskscited by 3
  13. 2025Mutual Information Tracks Policy Coherence in Reinforcement Learningcited by 3
  14. 2025Deep SPI: Safe Policy Improvement via World Modelscited by 3
  15. 2021Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metricscited by 2
  16. 2021Information-Bottleneck-Based Behavior Representation Learning for Multi-agent Reinforcement learningcited by 2
  17. 2021Component Transfer Learning for Deep RL Based on Abstract Representationscited by 2
  18. 2022Disentangled (Un)Controllable Featurescited by 2
  19. 2022Deep Reinforcement Learning with Vector Quantized Encodingcited by 2
  20. 2024Off-policy Evaluation with Deeply-abstracted Statescited by 2
  21. 2025Learning Abstract World Models with a Group-Structured Latent Spacecited by 1
  22. 2022SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learningcited by 0
  23. 2022elBERto: Self-supervised Commonsense Learning for Question Answeringcited by 0
  24. 2023Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learningcited by 0
  25. 2026Compositional Behavioral Semantics for State Abstraction in Reinforcement Learningcited by 0