mlsanityData to 7 Oct 2026

RIZE: Adaptive Regularization for Imitation Learning

arXiv 2502.20089 ↗First posted 27 Feb 2025cs.LG cs.AI cs.ROcited by 0

On the map: Offline RL and imitation learning from data → Inverse reinforcement learning

Abstract (arXiv)

We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization. Building on the Maximum Entropy IRL framework, our approach incorporates a squared temporal-difference (TD) regularizer with adaptive targets that evolve dynamically during training, thereby imposing adaptive bounds on recovered rewards and promoting robust decision-making. To capture richer return information, we integrate distributional RL into the learning process. Empirically, our method achieves expert-level performance on complex MuJoCo and Adroit environments, surpassing baseline methods on the Humanoid-v2 task with limited expert demonstrations. Extensive experiments and ablation studies further validate the effectiveness of the approach and provide insights into reward dynamics in imitation learning. Our source code is available at https://github.com/adibka/RIZE.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 32 of its 50 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

32 of 50 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching11 Nov
  2. 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning1 Mar

Other references · 30

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2017Deep reinforcement learning from human preferencescited by 3,846
  4. 2016Concrete Problems in AI Safetycited by 1,582
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  7. 2018DeepMind Control Suitecited by 935
  8. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  9. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  10. 2017Deep Reinforcement Learning that Matterscited by 727
  11. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  12. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
18 more
  1. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 464
  2. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  3. 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 362
  4. 2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 298
  5. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
  6. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 203
  7. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 191
  8. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 188
  9. 2019Imitation Learning via Off-Policy Distribution Matchingcited by 182
  10. 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RLcited by 136
  11. 2021Reward (Mis)design for Autonomous Drivingcited by 102
  12. 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 83
  13. 2023Inverse Preference Learning: Preference-based RL without a Reward Functioncited by 68
  14. 2022Proximal Point Imitation Learningcited by 25
  15. 2023Coherent Soft Imitation Learningcited by 21
  16. 2024Diffusing States and Matching Scores: A New Framework for Imitation Learningcited by 16
  17. 2024Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learningcited by 8
  18. 2024Adversarial Imitation Learning via Boostingcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024RILe: Reinforced Imitation Learning
  2. 2020Regularized Inverse Reinforcement Learning
  3. 2026Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning
  4. 2024Learning Causally Invariant Reward Functions from Diverse Demonstrations
  5. 2025Statistical analysis of Inverse Entropy-regularized Reinforcement Learning
  6. 2023A Novel Variational Lower Bound for Inverse Reinforcement Learning
  7. 2024Inverse Delayed Reinforcement Learning
  8. 2023BC-IRL: Learning Generalizable Reward Functions from Demonstrations