mlsanityData to 7 Oct 2026

Latent Wasserstein Adversarial Imitation Learning

arXiv 2603.05440 ↗First posted 5 Mar 2026cs.LGcited by 0

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

Abstract (arXiv)

Imitation Learning (IL) enables agents to mimic expert behavior by learning from demonstrations. However, traditional IL methods require large amounts of medium-to-high-quality demonstrations as well as actions of expert demonstrations, both of which are often unavailable. To reduce this need, we propose Latent Wasserstein Adversarial Imitation Learning (LWAIL), a novel adversarial imitation learning framework that focuses on state-only distribution matching. It benefits from the Wasserstein distance computed in a dynamics-aware latent space. This dynamics-aware latent space differs from prior work and is obtained via a pre-training stage, where we train the Intention Conditioned Value Function (ICVF) to capture a dynamics-aware structure of the state space using a small set of randomly generated state-only data. We show that this enhances the policy's understanding of state transitions, enabling the learning process to use only one or a few state-only expert episodes to achieve expert-level performance. Through experiments on multiple MuJoCo environments, we demonstrate that our method outperforms prior Wasserstein-based IL methods and prior adversarial IL methods, achieving better results across various tasks.

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 78 of its 94 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

78 of 94 references.

Closest ancestors · 28

Same direction, newest first

  1. 2024Reward-free World Models for Online Imitation Learning17 Oct
  2. 2024Diffusion Imitation from Observation7 Oct
  3. 2024OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning24 May
  4. 2024Efficient Imitation Learning with Conservative World Models21 May
  5. 2024Align Your Intents: Offline Imitation Learning via Optimal Transport20 Feb
  6. 2023DiffAIL: Diffusion Adversarial Imitation Learning11 Dec
  7. 2023Adversarial Imitation Learning from Visual Observations using Latent Information29 Sep
  8. 2023Coherent Soft Imitation Learning25 May
  9. 2022imitation: Clean Imitation Learning Implementations22 Nov
  10. 2022Planning for Sample Efficient Imitation Learning18 Oct
  11. 2022Discriminator-Guided Model-Based Offline Imitation Learning1 Jul
  12. 2022Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching4 Feb
16 more
  1. 2021Cross-Domain Imitation Learning via Optimal Transport7 Oct
  2. 2021A Pragmatic Look at Deep Imitation Learning4 Aug
  3. 2021Visual Adversarial Imitation Learning using Variational Models16 Jul
  4. 2021IQ-Learn: Inverse soft-Q Learning for Imitation23 Jun
  5. 2021SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching6 Jun
  6. 2021No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODE3 Apr
  7. 2021Off-Policy Imitation Learning from Observations25 Feb
  8. 2021MobILE: Model-Based Imitation Learning From Observation Alone22 Feb
  9. 2020Offline Learning from Demonstrations and Unlabeled Experience27 Nov
  10. 2020Primal Wasserstein Imitation Learning8 Jun
  11. 2020Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration5 Jun
  12. 2019Imitation Learning via Off-Policy Distribution Matching10 Dec
  13. 2019Wasserstein Adversarial Imitation Learning19 Jun
  14. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep
  15. 2018Generative Adversarial Imitation from Observation17 Jul
  16. 2018Behavioral Cloning from Observation4 May

Other references · 50

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2015Continuous control with deep reinforcement learningcited by 3,279
  6. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2016Generative Adversarial Imitation Learningcited by 1,576
  9. 2018World Modelscited by 1,444
  10. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  11. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
  12. 2023Mastering Diverse Domains through World Modelscited by 1,193
38 more
  1. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  2. 2020Mastering Atari with Discrete World Modelscited by 990
  3. 2018DeepMind Control Suitecited by 935
  4. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  5. 2024Genie: Generative Interactive Environmentscited by 706
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  7. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  8. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  9. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 244
  10. 2020FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPscited by 232
  11. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  12. 2019What Can Neural Networks Reason About?cited by 155
  13. 2021The Surprising Effectiveness of Representation Learning for Visual Imitationcited by 149
  14. 2019Unsupervised State Representation Learning in Ataricited by 144
  15. 2019Scalable methods for computing state similarity in deterministic Markov Decision Processescited by 133
  16. 2021Representation Learning for Online and Offline RL in Low-rank MDPscited by 128
  17. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  18. 2021OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimationcited by 121
  19. 2023Policy Expansion for Bridging Offline-to-Online Reinforcement Learningcited by 103
  20. 2021Model-free Representation Learning and Exploration in Low-rank MDPscited by 82
  21. 2018Generative Adversarial User Model for Reinforcement Learning Based Recommendation Systemcited by 64
  22. 2023Reinforcement Learning from Passive Data via Latent Intentionscited by 64
  23. 2021Towards Robust Bisimulation Metric Learningcited by 49
  24. 2023Optimal Transport for Offline Imitation Learningcited by 42
  25. 2019Positive-Unlabeled Reward Learningcited by 36
  26. 2021Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)cited by 33
  27. 2016Model-based Adversarial Imitation Learningcited by 29
  28. 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learningcited by 28
  29. 2021Metrics and continuity in reinforcement learningcited by 26
  30. 2021MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learningcited by 24
  31. 2022LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimationcited by 22
  32. 2021GridToPix: Training Embodied Agents with Minimal Supervisioncited by 20
  33. 2023CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learningcited by 20
  34. 2019Model-based Behavioral Cloning with Future Image Similarity Learningcited by 8
  35. 2023Offline Imitation from Observation via Primal Wasserstein State Occupancy Matchingcited by 5
  36. 2023A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectoriescited by 3
  37. 2024Self-evolving Autoencoder Embedded Q-Networkcited by 2
  38. 2023Suppressing Overestimation in Q-Learning through Adversarial Behaviorscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Provably Efficient Adversarial Imitation Learning with Unknown Transitions
  2. 2022Latent Policies for Adversarial Imitation Learning
  3. 2023Sample-efficient Adversarial Imitation Learning
  4. 2020State-only Imitation with Transition Dynamics Mismatch
  5. 2020ADAIL: Adaptive Adversarial Imitation Learning
  6. 2023Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning
  7. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraints
  8. 2021Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency