mlsanityData to 14 Oct 2026

Sample-efficient Adversarial Imitation Learning from Observation

arXiv 1906.07374 ↗First posted 18 Jun 2019cs.LG stat.MLcited by 6

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

Abstract (arXiv)

Imitation from observation is the framework of learning tasks by observing demonstrated state-only trajectories. Recently, adversarial approaches have achieved significant performance improvements over other methods for imitating complex behaviors. However, these adversarial imitation algorithms often require many demonstration examples and learning iterations to produce a policy that is successful at imitating a demonstrator's behavior. This high sample complexity often prohibits these algorithms from being deployed on physical robots. In this paper, we propose an algorithm that addresses the sample inefficiency problem by utilizing ideas from trajectory centric reinforcement learning algorithms. We test our algorithm and conduct experiments using an imitation task on a physical robot arm and its simulated version in Gazebo and will show the improvement in learning rate and efficiency.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 16 of its 32 references that are in the map. First posted on arXiv 18 Jun 2019.

Builds on

16 of 32 references.

Closest ancestors · 6

Same direction, newest first

  1. 2019Recent Advances in Imitation Learning from Observation30 May
  2. 2019Imitation Learning from Video by Leveraging Proprioception22 May
  3. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep
  4. 2018Multi-Agent Generative Adversarial Imitation Learning26 Jul
  5. 2018Generative Adversarial Imitation from Observation17 Jul
  6. 2018Behavioral Cloning from Observation4 May

Other references · 10

  1. 2015Trust Region Policy Optimizationcited by 2,580
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2016Generative Adversarial Imitation Learningcited by 1,597
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  5. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  7. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
  8. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  9. 2017Third-Person Imitation Learningcited by 103
  10. 2015Learning Contact-Rich Manipulation Skills with Guided Policy Searchcited by 38

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 2; 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 1.

6 papers.

  1. 2020Imitation Learning with Sinkhorn Distancescited by 30
  2. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  3. 2022State Advantage Weighting for Offline RLcited by 5
  4. 2021DEALIO: Data-Efficient Adversarial Learning for Imitation from Observationcited by 4
  5. 2023Sample-efficient Adversarial Imitation Learningcited by 0
  6. 2026Online World Modeling Enables Real-World Inverse Reinforcement Learning from Observationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency
  2. 2023Adversarial Imitation Learning from Visual Observations using Latent Information
  3. 2019Provably Efficient Imitation Learning from Observation Alone
  4. 2020ADAIL: Adaptive Adversarial Imitation Learning
  5. 2023Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning
  6. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets
  7. 2021RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning
  8. 2022Planning for Sample Efficient Imitation Learning