mlsanityData to 7 Oct 2026

Domain-Robust Visual Imitation Learning with Mutual Information Constraints

arXiv 2103.05079 ↗First posted 8 Mar 2021cs.LG cs.AIcited by 20

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

Abstract (arXiv)

Human beings are able to understand objectives and learn by simply observing others perform a task. Imitation learning methods aim to replicate such capabilities, however, they generally depend on access to a full set of optimal states and actions taken with the agent's actuators and from the agent's point of view. In this paper, we introduce a new algorithm - called Disentangling Generative Adversarial Imitation Learning (DisentanGAIL) - with the purpose of bypassing such constraints. Our algorithm enables autonomous agents to learn directly from high dimensional observations of an expert performing a task, by making use of adversarial learning with a latent representation inside the discriminator network. Such latent representation is regularized through mutual information constraints to incentivize learning only features that encode information about the completion levels of the task being demonstrated. This allows to obtain a shared feature space to successfully perform imitation while disregarding the differences between the expert's and the agent's domains. Empirically, our algorithm is able to efficiently imitate in a diverse range of control problems including balancing, manipulation and locomotive tasks, while being robust to various domain differences in terms of both environment appearance and agent embodiment.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 32 of its 45 references that are in the map. First posted on arXiv 8 Mar 2021.

Builds on

32 of 45 references.

Closest ancestors · 7

Same direction, newest first

  1. 2020Cross-Domain Imitation Learning with a Dual Structure2 Jun
  2. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learning31 Jan
  3. 2019Task-Relevant Adversarial Imitation Learning2 Oct
  4. 2019Domain Adaptive Imitation Learning30 Sep
  5. 2019Recent Advances in Imitation Learning from Observation30 May
  6. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow1 Oct
  7. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep

Other references · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2015Continuous control with deep reinforcement learningcited by 3,279
  6. 2015Trust Region Policy Optimizationcited by 2,503
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  10. 2016Generative Adversarial Imitation Learningcited by 1,576
  11. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  12. 2018MINE: Mutual Information Neural Estimationcited by 680
13 more
  1. 2017Wasserstein GANcited by 635
  2. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  3. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  4. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  5. 2015Maximum Entropy Deep Inverse Reinforcement Learningcited by 173
  6. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 167
  7. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  8. 2019AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videoscited by 105
  9. 2017Third-Person Imitation Learningcited by 103
  10. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 84
  11. 2019Third-Person Visual Imitation Learning via Decoupled Hierarchical Controllercited by 73
  12. 2013Equitability, mutual information, and the maximal information coefficientcited by 45
  13. 2016Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstrationcited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 6; 2024: 6; 2025: 3; 2026: 1.

20 papers.

Sort:

By area:

  1. 2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 74
  2. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transportcited by 64
  3. 2023See to Touch: Learning Tactile Dexterity through Visual Incentivescited by 33
  4. 2022Learn what matters: cross-domain imitation learning with task-relevant embeddingscited by 14
  5. 2023Domain Adaptive Imitation Learning with Visual Observationcited by 11
  6. 2023SeMAIL: Eliminating Distractors in Visual Imitation via Separated Modelscited by 10
  7. 2023Adversarial Imitation Learning from Visual Observations using Latent Informationcited by 10
  8. 2024VIEW: Visual Imitation Learning with Waypointscited by 10
  9. 2024Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learningcited by 9
  10. 2024xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editingcited by 9
  11. 2023Robust Visual Imitation Learning with Inverse Dynamics Representationscited by 8
  12. 2021Cross Domain Robot Imitation with Invariant Representationcited by 7
8 more
  1. 2022Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemblecited by 5
  2. 2024Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversioncited by 4
  3. 2024DIDA: Denoised Imitation Learning based on Domain Adaptationcited by 2
  4. 2024SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoringcited by 1
  5. 2025Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videoscited by 1
  6. 2025Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observationscited by 0
  7. 2025Learning from Observation: A Survey of Recent Advancescited by 0
  8. 2026Reinforcement Learning from Cross-domain Videos with Video Prediction Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Latent Policies for Adversarial Imitation Learning
  2. 2026Latent Wasserstein Adversarial Imitation Learning
  3. 2025State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning
  4. 2020ADAIL: Adaptive Adversarial Imitation Learning
  5. 2021Visual Adversarial Imitation Learning using Variational Models
  6. 2018Generative Adversarial Imitation from Observation
  7. 2023Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning
  8. 2023Sample-efficient Adversarial Imitation Learning