mlsanityData to 7 Oct 2026

Abstraction for Deep Reinforcement Learning

arXiv 2202.05839 ↗First posted 10 Feb 2022cs.LG cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

We characterise the problem of abstraction in the context of deep reinforcement learning. Various well established approaches to analogical reasoning and associative memory might be brought to bear on this issue, but they present difficulties because of the need for end-to-end differentiability. We review developments in AI and machine learning that could facilitate their adoption.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 37 of its 89 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

37 of 89 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  8. 2020Object-Centric Learning with Slot Attentioncited by 865
  9. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  10. 2020Hopfield Networks is All You Needcited by 461
  11. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  12. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
25 more
  1. 2016Dense Associative Memory for Pattern Recognitioncited by 230
  2. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  3. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  4. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 225
  5. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  6. 2018Measuring abstract reasoning in neural networkscited by 165
  7. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159
  8. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  9. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 147
  10. 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 137
  11. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  12. 2020Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learningcited by 101
  13. 2017Building machines that adapt and compute like brainscited by 99
  14. 2021Coordination Among Neural Modules Through a Shared Global Workspacecited by 83
  15. 2017Learning with Latent Languagecited by 75
  16. 2018Temporal Difference Variational Auto-Encodercited by 48
  17. 2016Towards Deep Symbolic Reinforcement Learningcited by 42
  18. 2018Investigating Human Priors for Playing Video Gamescited by 39
  19. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  20. 2019Making sense of sensory inputcited by 29
  21. 2018Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programscited by 21
  22. 2021CoBERL: Contrastive BERT for Reinforcement Learningcited by 20
  23. 2021Unsupervised Object-Based Transition Models for 3D Partially Observable Environmentscited by 19
  24. 2018The Kanerva Machine: A Generative Distributed Memorycited by 13
  25. 2020Neural Analogical Matchingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 6; 2024: 3; 2025: 1; 2026: 1.

19 papers.

Sort:

By area:

  1. 2022Talking About Large Language Modelscited by 174
  2. 2022Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoningcited by 33
  3. 2022Emergent Bartering Behaviour in Multi-Agent Reinforcement Learningcited by 18
  4. 2023A Definition of Open-Ended Learning Problems for Goal-Conditioned Agentscited by 16
  5. 2022Language and Culture Internalisation for Human-Like Autotelic AIcited by 14
  6. 2023Schema-learning and rebinding as mechanisms of in-context learning and emergencecited by 14
  7. 2022Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learningcited by 9
  8. 2022A Rubric for Human-like Agents and NeuroAIcited by 8
  9. 2023Graph schemas as abstractions for transfer learning, inference, and planningcited by 7
  10. 2023Multi Time Scale World Modelscited by 7
  11. 2022Language Models Understand Us, Poorlycited by 3
  12. 2024Overcoming classic challenges for artificial neural networks by providing incentives and practicecited by 3
7 more
  1. 2023Strategy Extraction in Single-Agent Gamescited by 1
  2. 2023Cooperative Multi-Agent Learning for Navigation via Structured State Abstractioncited by 1
  3. 2024Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspectivecited by 1
  4. 2024Causal prompting model-based offline reinforcement learningcited by 1
  5. 2025A Representationalist, Functionalist and Naturalistic Conception of Intelligence as a Foundation for AGIcited by 1
  6. 2022AIGenC: An AI generalisation model via creativitycited by 0
  7. 2026PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Gamescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
  2. 2024ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
  3. 2024Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL
  4. 2025AR2: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
  5. 2025Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning
  6. 2026Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents
  7. 2026On the Role of Computation in Reinforcement Learning
  8. 2025A Survey on Explainable Deep Reinforcement Learning