mlsanityData to 14 Oct 2026

Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation

arXiv 2304.10260 ↗First posted 19 Apr 2023cs.LG cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Domain-adaptive trajectory imitation is a skill that some predators learn for survival, by mapping dynamic information from one domain (their speed and steering direction) to a different domain (current position of the moving prey). An intelligent agent with this skill could be exploited for a diversity of tasks, including the recognition of abnormal motion in traffic once it has learned to imitate representative trajectories. Towards this direction, we propose DATI, a deep reinforcement learning agent designed for domain-adaptive trajectory imitation using a cycle-consistent generative adversarial method. Our experiments on a variety of synthetic families of reference trajectories show that DATI outperforms baseline methods for imitation learning and optimal control in this setting, keeping the same per-task hyperparameters. Its generalization to a real-world scenario is shown through the discovery of abnormal motion patterns in maritime traffic, opening the door for the use of deep reinforcement learning methods for spatially-unconstrained trajectory data mining.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 52 references that are in the map. First posted on arXiv 19 Apr 2023.

Builds on

16 of 52 references.

References · 16

  1. 2017Improved Training of Wasserstein GANscited by 2,235
  2. 2016OpenAI Gymcited by 1,736
  3. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  4. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  5. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 285
  6. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
  7. 2019Time2Vec: Learning a Vector Representation of Timecited by 213
  8. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 204
  9. 2018Learning to Walk via Deep Reinforcement Learningcited by 158
  10. 2021Cross-domain Imitation from Observationscited by 42
  11. 2020Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvaluescited by 27
  12. 2018SFV: Reinforcement Learning of Physical Skills from Videoscited by 20
4 more
  1. 2020Learning to Fly via Deep Model-Based Reinforcement Learningcited by 20
  2. 2020Sequential Anomaly Detection using Inverse Reinforcement Learningcited by 20
  3. 2020Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotioncited by 10
  4. 2020Optimal Any-Angle Pathfinding on a Spherecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving
  2. 2025Generative Modeling for Adversarial Lane-Change Scenarios ↗
  3. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
  4. 2025Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline
  5. 2022Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
  6. 2021A Pragmatic Look at Deep Imitation Learning
  7. 2020TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning
  8. 2021Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments