mlsanityData to 7 Oct 2026

Imagination-Augmented Agents for Deep Reinforcement Learning

arXiv 1707.06203 ↗First posted 19 Jul 2017cs.LG cs.AI stat.MLcited by 137

Not on the map. Why?

Abstract (arXiv)

We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to interpret predictions from a learned environment model to construct implicit plans in arbitrary ways, by using the predictions as additional context in deep policy networks. I2As show improved data efficiency, performance, and robustness to model misspecification compared to several baselines.

Key facts. Cited by 137 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 46; 2022: 29; 2023: 23; 2024: 13; 2025: 17; 2026: 8.

137 papers.

Sort:

By area:

  1. 2022A Generalist Agentcited by 802
  2. 2020MOPO: Model-based Offline Policy Optimizationcited by 630
  3. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RLcited by 244
  4. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  5. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  6. 2023Structured World Models from Human Videoscited by 144
  7. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
  8. 2021Representation Matters: Offline Pretraining for Sequential Decision Makingcited by 90
  9. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 82
  10. 2023Level Generation Through Large Language Modelscited by 68
  11. 2022A Survey on Model-based Reinforcement Learningcited by 65
  12. 2021Predicting Video with VQVAEcited by 61
38 more
  1. 2021Learning Task Informed Abstractionscited by 58
  2. 2021Muesli: Combining Improvements in Policy Optimizationcited by 53
  3. 2022Retrieval-Augmented Reinforcement Learningcited by 53
  4. 2021Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planningcited by 43
  5. 2021MBRL-Lib: A Modular Library for Model-based Reinforcement Learningcited by 41
  6. 2022COLA: Consistent Learning with Opponent-Learning Awarenesscited by 38
  7. 2022Spectral Decomposition Representation for Reinforcement Learningcited by 35
  8. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  9. 2021Procedural Generalization by Planning with Self-Supervised World Modelscited by 30
  10. 2022Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objectivecited by 28
  11. 2021Self-Imitation Learning by Planningcited by 25
  12. 2021Differentiable Spatial Planning using Transformerscited by 25
  13. 2025LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulationcited by 24
  14. 2025ViPRA: Video Prediction for Robot Actionscited by 24
  15. 2021Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Controlcited by 22
  16. 2021Subgoal Search For Complex Reasoning Taskscited by 21
  17. 2021Neural Algorithmic Reasoners are Implicit Plannerscited by 21
  18. 2021Policy-Guided Heuristic Search with Guaranteescited by 20
  19. 2021Unsupervised Object-Based Transition Models for 3D Partially Observable Environmentscited by 19
  20. 2022Abstraction for Deep Reinforcement Learningcited by 19
  21. 2022A Survey on Reinforcement Learning in Aviation Applicationscited by 19
  22. 2021Reinforcement Learning for Feedback-Enabled Cyber Resiliencecited by 18
  23. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  24. 2021There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learningcited by 17
  25. 2021Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learningcited by 17
  26. 2024A Philosophical Introduction to Language Models - Part II: The Way Forwardcited by 17
  27. 2025Meta-RL Induces Exploration in Language Agentscited by 17
  28. 2026RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedbackcited by 16
  29. 2023Hierarchical Imitation Learning with Vector Quantized Modelscited by 15
  30. 2021Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Modelcited by 14
  31. 2023Neuro-Symbolic World Models for Adapting to Open World Noveltycited by 14
  32. 2024Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Modelscited by 14
  33. 2025General agents contain world modelscited by 14
  34. 2021High-Accuracy Model-Based Reinforcement Learning, a Surveycited by 13
  35. 2023Thinker: Learning to Plan and Actcited by 13
  36. 2022Goal-Space Planning with Subgoal Modelscited by 12
  37. 2025Probabilistic Shielding for Safe Reinforcement Learningcited by 12
  38. 2021Neuro-algorithmic Policies enable Fast Combinatorial Generalizationcited by 11

50 most cited of 137 All 137 (JSON)