mlsanityData to 7 Oct 2026

Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning

arXiv 2407.12792 ↗First posted 18 Jun 2024cs.LG cs.CVcited by 9

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

Abstract (arXiv)

We propose C-LAIfO, a computationally efficient algorithm designed for imitation learning from videos in the presence of visual mismatch between agent and expert domains. We analyze the problem of imitation from expert videos with visual discrepancies, and introduce a solution for robust latent space estimation using contrastive learning and data augmentation. Provided a visually robust latent space, our algorithm performs imitation entirely within this space using off-policy adversarial imitation learning. We conduct a thorough ablation study to justify our design and test C-LAIfO on high-dimensional continuous robotic tasks. Additionally, we demonstrate how C-LAIfO can be combined with other reward signals to facilitate learning on a set of challenging hand manipulation tasks with sparse rewards. Our experiments show improved performance compared to baseline methods, highlighting the effectiveness of C-LAIfO. To ensure reproducibility, we open source our code.

Key facts. Cited by 9 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 40 of its 51 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

40 of 51 references.

Closest ancestors · 19

Same direction, newest first

  1. 2023Domain Adaptive Imitation Learning with Visual Observation1 Dec
  2. 2023Adversarial Imitation Learning from Visual Observations using Latent Information29 Sep
  3. 2023Visual Imitation Learning with Patch Rewards2 Feb
  4. 2022Imitation Learning from Observations under Transition Model Disparity25 Apr
  5. 2021Cross-Domain Imitation Learning via Optimal Transport7 Oct
  6. 2021Visual Adversarial Imitation Learning using Variational Models16 Jul
  7. 2021Cross-domain Imitation from Observations20 May
  8. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraints8 Mar
  9. 2021Off-Policy Imitation Learning from Observations25 Feb
  10. 2021MobILE: Model-Based Imitation Learning From Observation Alone22 Feb
  11. 2020On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration16 Oct
  12. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learning31 Jan
7 more
  1. 2019Imitation Learning via Off-Policy Distribution Matching10 Dec
  2. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  3. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement10 Oct
  4. 2019Learning Belief Representations for Imitation Learning in POMDPs22 Jun
  5. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep
  6. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets6 Sep
  7. 2018Generative Adversarial Imitation from Observation17 Jul

Other references · 21

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2015Continuous control with deep reinforcement learningcited by 3,279
  6. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2016Generative Adversarial Imitation Learningcited by 1,576
  9. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  10. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  11. 2018DeepMind Control Suitecited by 935
  12. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
9 more
  1. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  2. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  3. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  4. 2019AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videoscited by 105
  5. 2017Third-Person Imitation Learningcited by 103
  6. 2022VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learningcited by 51
  7. 2023SLoMo: A General System for Legged Robot Motion Imitation from Casual Videoscited by 10
  8. 2022Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigationcited by 4
  9. 2023A Reinforcement Learning Approach for Robotic Unloading from Visual Observationscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 4.

9 papers.

  1. 2025Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuningcited by 8
  2. 2025Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representationscited by 4
  3. 2024Spatially Visual Perception for End-to-End Robotic Learningcited by 2
  4. 2025Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videoscited by 1
  5. 2025Robust Point Cloud Reinforcement Learning via PCA-Based Canonicalizationcited by 1
  6. 2026Semi-Supervised Cross-Domain Imitation Learningcited by 1
  7. 2026Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RLcited by 1
  8. 2026Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learningcited by 0
  9. 2026Reinforcement Learning from Cross-domain Videos with Video Prediction Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Adversarial Imitation Learning from Video using a State Observer
  2. 2024Visual Imitation Learning with Calibrated Contrastive Representation
  3. 2026Latent Wasserstein Adversarial Imitation Learning
  4. 2019Task-Relevant Adversarial Imitation Learning
  5. 2026It's Not Just More Demos: Counterfactual Action Sensitivity Coverage for Data-Efficient Robust Robot Imitation
  6. 2018Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning
  7. 2026Difference-Aware Retrieval Policies for Imitation Learning
  8. 2022Latent Policies for Adversarial Imitation Learning