mlsanityData to 7 Oct 2026

Deep Reinforcement and InfoMax Learning

arXiv 2006.07217 ↗First posted 12 Jun 2020cs.LG stat.MLcited by 79

Not on the map. Why?

Abstract (arXiv)

We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving and adapting to new RL problems. To test that hypothesis, we introduce an objective based on Deep InfoMax (DIM) which trains the agent to predict the future by maximizing the mutual information between its internal representation of successive timesteps. We test our approach in several synthetic settings, where it successfully learns representations that are predictive of the future. Finally, we augment C51, a strong RL baseline, with our temporal DIM objective and demonstrate improved performance on a continual learning task and on the recently introduced Procgen environment.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 26; 2023: 23; 2024: 11; 2025: 2; 2026: 1.

79 papers.

Sort:

By area:

  1. 2022Masked World Models for Visual Controlcited by 169
  2. 2023Bigger, Better, Faster: Human-level Atari with human-level efficiencycited by 145
  3. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  4. 2022Reinforcement Learning with Action-Free Pre-Training from Videoscited by 107
  5. 2021Pretraining Representations for Data-Efficient Reinforcement Learningcited by 105
  6. 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 81
  7. 2021Learning Task Informed Abstractionscited by 58
  8. 2023TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learningcited by 56
  9. 2022Retrieval-Augmented Reinforcement Learningcited by 53
  10. 2024Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Makingcited by 53
  11. 2024Bridging State and History Representations: Understanding Self-Predictive RLcited by 52
  12. 2022Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Modelscited by 42
38 more
  1. 2023PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learningcited by 42
  2. 2021PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learningcited by 41
  3. 2022Mask-based Latent Reconstruction for Reinforcement Learningcited by 39
  4. 2023Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learningcited by 37
  5. 2021Return-Based Contrastive Representation Learning for Reinforcement Learningcited by 36
  6. 2021DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneckcited by 31
  7. 2021Procedural Generalization by Planning with Self-Supervised World Modelscited by 30
  8. 2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 30
  9. 2021Which Mutual-Information Representation Learning Objectives are Sufficient for Control?cited by 28
  10. 2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learningcited by 27
  11. 2023Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stagescited by 27
  12. 2023Behavior Contrastive Learning for Unsupervised Skill Discoverycited by 26
  13. 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
  14. 2021Decomposed Mutual Information Estimation for Contrastive Representation Learningcited by 24
  15. 2022Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?cited by 24
  16. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 23
  17. 2023Learning World Models with Identifiable Factorizationcited by 23
  18. 2024Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasetscited by 23
  19. 2021Dynamic Bottleneck for Robust Self-Supervised Explorationcited by 21
  20. 2021Cross-Trajectory Representation Learning for Zero-Shot Generalization in RLcited by 20
  21. 2021CoBERL: Contrastive BERT for Reinforcement Learningcited by 20
  22. 2023Explore to Generalize in Zero-Shot RLcited by 20
  23. 2021Domain Adversarial Reinforcement Learningcited by 19
  24. 2022Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learningcited by 19
  25. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  26. 2022Pretraining in Deep Reinforcement Learning: A Surveycited by 18
  27. 2021Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functionscited by 17
  28. 2022Learning Bellman Complete Representations for Offline Policy Evaluationcited by 17
  29. 2025A Survey of State Representation Learning for Deep Reinforcement Learningcited by 17
  30. 2022An Empirical Investigation of Representation Learning for Imitationcited by 15
  31. 2022Agent-Controller Representations: Principled Offline RL with Rich Exogenous Informationcited by 15
  32. 2022Contrastive Value Learning: Implicit Models for Simple Offline RLcited by 15
  33. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddingscited by 14
  34. 2022Representation Learning in Deep RL via Discrete Information Bottleneckcited by 13
  35. 2023Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractionscited by 13
  36. 2022Behavior Prior Representation learning for Offline Reinforcement Learningcited by 12
  37. 2022Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Visioncited by 11
  38. 2022Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learningcited by 10

50 most cited of 79 All 79 (JSON)