mlsanityData to 7 Oct 2026

Distributional Active Inference

arXiv 2601.20985 ↗First posted 28 Jan 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning framework addresses only the latter, it tends to deliver sample-inefficient solutions. Active inference is the state-of-the-art process theory that explains how biological brains handle this dual problem. However, its applications to artificial intelligence have thus far been limited to extensions of existing model-based approaches. We present a formal abstraction of reinforcement learning algorithms that spans model-based, distributional, and model-free approaches. This abstraction seamlessly integrates active inference into the distributional reinforcement learning framework, making its performance advantages accessible without transition dynamics modeling.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 65 of its 100 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

65 of 100 references.

References · 65

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  5. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  6. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  7. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  8. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  9. 2018Exploration by Random Network Distillationcited by 966
  10. 2018DeepMind Control Suitecited by 935
  11. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  12. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
38 more
  1. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 464
  2. 2017Wasserstein Auto-Encoderscited by 371
  3. 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 362
  4. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  5. 2017Count-Based Exploration with Neural Density Modelscited by 255
  6. 2013(More) Efficient Reinforcement Learning via Posterior Samplingcited by 233
  7. 2018Distributed Distributional Deterministic Policy Gradientscited by 195
  8. 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 154
  9. 2020Active inference on discrete state-spaces: a synthesiscited by 91
  10. 2019Better Exploration with Optimistic Actor-Criticcited by 88
  11. 2019Fully Parameterized Quantile Function for Distributional Reinforcement Learningcited by 87
  12. 2020Deep active inference agents using Monte-Carlo methodscited by 72
  13. 2018Probabilistic Recurrent State-Space Modelscited by 64
  14. 2017Near Optimal Behavior via Approximate State Abstractioncited by 63
  15. 2019Being Optimistic to Be Conservative: Quickly Learning a CVaR Policycited by 63
  16. 2019Distributional Reinforcement Learning for Efficient Explorationcited by 59
  17. 2019Deep Active Inference as Variational Policy Gradientscited by 52
  18. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  19. 2020Reinforcement Learning through Active Inferencecited by 47
  20. 2017Deep Active Inferencecited by 44
  21. 2022Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robotscited by 44
  22. 2020On the Relationship Between Active Inference and Control as Inferencecited by 42
  23. 2024Exploration and Anti-Exploration with Distributional Random Network Distillationcited by 32
  24. 2020Action and Perception as Divergence Minimizationcited by 31
  25. 2019Scaling active inferencecited by 30
  26. 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximizationcited by 30
  27. 2021Contrastive Active Inferencecited by 21
  28. 2020Deep Active Inference for Partially Observable MDPscited by 20
  29. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  30. 2023Robust Quadrupedal Locomotion via Risk-Averse Policy Learningcited by 16
  31. 2019Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulatorcited by 15
  32. 2021Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learningcited by 15
  33. 2021GMAC: A Distributional Perspective on Actor-Critic Frameworkcited by 15
  34. 2018Exploration by Distributional Reinforcement Learningcited by 13
  35. 2021Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learningcited by 13
  36. 2019Bayesian policy selection using active inferencecited by 12
  37. 2020Sample-based Distributional Policy Gradientcited by 12
  38. 2021An empirical evaluation of active inference in multi-armed banditscited by 12

50 most cited of 65 All 65 (JSON)

Built on by

Not cited yet.