mlsanityData to 7 Oct 2026

C-Learning: Learning to Achieve Goals via Recursive Classification

arXiv 2011.08909 ↗First posted 17 Nov 2020cs.LG cs.AIcited by 99

Not on the map. Why?

Cited by 21 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We study the problem of predicting and controlling the future state distribution of an autonomous agent. This problem, which can be viewed as a reframing of goal-conditioned reinforcement learning (RL), is centered around learning a conditional probability density function over future states. Instead of directly estimating this density function, we indirectly estimate this density function by training a classifier to predict whether an observation comes from the future. Via Bayes' rule, predictions from our classifier can be transformed into predictions over future states. Importantly, an off-policy variant of our algorithm allows us to predict the future state distribution of a new policy, without collecting new experience. This variant allows us to optimize functionals of a policy's future state distribution, such as the density of reaching a particular goal state. While conceptually similar to Q-learning, our work lays a principled foundation for goal-conditioned RL as density estimation, providing justification for goal-conditioned methods used in prior work. This foundation makes hypotheses about Q-learning, including the optimal goal-sampling ratio, which we confirm experimentally. Moreover, our proposed method is competitive with prior goal-conditioned RL methods.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 16; 2023: 13; 2024: 18; 2025: 19; 2026: 20.

99 papers.

Sort:

By area:

  1. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  2. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  3. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 133
  4. 2021Goal-Conditioned Reinforcement Learning with Imagined Subgoalscited by 129
  5. 2021Rapid Exploration for Open-World Navigation with Latent Goal Modelscited by 118
  6. 2023Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learningcited by 116
  7. 2021Learning One Representation to Optimize All Rewardscited by 110
  8. 2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 105
  9. 2024Vision Language Models are In-Context Value Learnerscited by 84
  10. 2022Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?cited by 70
  11. 2022How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regressioncited by 65
  12. 2022Motion Policy Networkscited by 53
38 more
  1. 2024Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Makingcited by 53
  2. 2021Adversarial Intrinsic Motivation for Reinforcement Learningcited by 40
  3. 20251000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilitiescited by 39
  4. 2021Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classificationcited by 38
  5. 2021The Information Geometry of Unsupervised Reinforcement Learningcited by 36
  6. 2021Mismatched No More: Joint Model-Policy Optimization for Model-Based RLcited by 35
  7. 2023Contrastive Difference Predictive Codingcited by 35
  8. 2024Autonomous Improvement of Instruction Following Skills via Foundation Modelscited by 32
  9. 2022Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Spacecited by 31
  10. 2022Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Taskscited by 24
  11. 2023SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learningcited by 21
  12. 2024A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoalscited by 20
  13. 2023Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Datacited by 19
  14. 2023Distance Weighted Supervised Learning for Offline Interaction Datacited by 18
  15. 2024Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learningcited by 18
  16. 2021Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learningcited by 17
  17. 2021Understanding the World Through Actioncited by 17
  18. 2022Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learningcited by 16
  19. 2022Understanding the Complexity Gains of Single-Task RL with a Curriculumcited by 16
  20. 2023Pre-Training and Fine-Tuning Generative Flow Networkscited by 16
  21. 2021C-Planning: An Automatic Curriculum for Learning Goal-Reaching Taskscited by 15
  22. 2022Contrastive Value Learning: Implicit Models for Simple Offline RLcited by 15
  23. 2023Learning Video-Conditioned Policies for Unseen Manipulation Taskscited by 15
  24. 2024A Distributional Analogue to the Successor Representationcited by 15
  25. 2024Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inferencecited by 15
  26. 2024Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulationcited by 15
  27. 2021Offline Inverse Reinforcement Learningcited by 14
  28. 2023f-Policy Gradients: A General Framework for Goal Conditioned RL using f-Divergencescited by 14
  29. 2022Learning Robotic Navigation from Experience: Principles, Methods, and Recent Resultscited by 13
  30. 2025Normalizing Flows are Capable Models for Continuous Controlcited by 13
  31. 2021Learning Domain Invariant Representations in Goal-conditioned Block MDPscited by 12
  32. 2022A System for Morphology-Task Generalization via Unified Representation and Behavior Distillationcited by 12
  33. 2024Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weightingcited by 12
  34. 2025Transitive RL: Value Learning via Divide and Conquercited by 12
  35. 2022Generalised Policy Improvement with Geometric Policy Compositioncited by 11
  36. 2022Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learningcited by 10
  37. 2023Value function estimation using conditional diffusion models for controlcited by 10
  38. 2024Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNetscited by 8

50 most cited of 99 All 99 (JSON)