mlsanityData to 7 Oct 2026

Reinforced Imitation Learning by Free Energy Principle

arXiv 2107.11811 ↗First posted 25 Jul 2021cs.LG cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Reinforcement Learning (RL) requires a large amount of exploration especially in sparse-reward settings. Imitation Learning (IL) can learn from expert demonstrations without exploration, but it never exceeds the expert's performance and is also vulnerable to distributional shift between demonstration and execution. In this paper, we radically unify RL and IL based on Free Energy Principle (FEP). FEP is a unified Bayesian theory of the brain that explains perception, action and model learning by a common fundamental principle. We present a theoretical extension of FEP and derive an algorithm in which an agent learns the world model that internalizes expert demonstrations and at the same time uses the model to infer the current and future states and actions that maximize rewards. The algorithm thus reduces exploration costs by partially imitating experts as well as maximizing its return in a seamless way, resulting in a higher performance than the suboptimal expert. Our experimental results show that this approach is promising in visual control tasks especially in sparse-reward environments.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 33 references that are in the map. First posted on arXiv 25 Jul 2021.

Builds on

19 of 33 references.

Closest ancestors · 3

Same direction, newest first

  1. 2019SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards27 May
  2. 2018Deep Imitative Models for Flexible Inference, Planning, and Control15 Oct
  3. 2018Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning29 May

Other references · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  5. 2018World Modelscited by 1,444
  6. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  7. 2018DeepMind Control Suitecited by 935
  8. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  9. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 466
  10. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 322
  11. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 302
  12. 2019Deep Active Inference as Variational Policy Gradientscited by 52
4 more
  1. 2019Making Efficient Use of Demonstrations to Solve Hard Exploration Problemscited by 45
  2. 2017Deep Active Inferencecited by 44
  3. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrationscited by 35
  4. 2018Dual Policy Iterationcited by 22

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2019Reinforced Imitation in Heterogeneous Action Space
  2. 2020Energy-Based Imitation Learning
  3. 2024Free Energy Projective Simulation (FEPS): Active inference with interpretability
  4. 2024Reward-free World Models for Online Imitation Learning
  5. 2024A Bayesian Solution To The Imitation Gap
  6. 2019Bayesian policy selection using active inference
  7. 2026Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
  8. 2021Imitation Learning by Reinforcement Learning