mlsanityData to 7 Oct 2026

Support-weighted Adversarial Imitation Learning

arXiv 2002.08803 ↗First posted 20 Feb 2020cs.LG stat.MLcited by 3

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

Abstract (arXiv)

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of demonstrations, it faces several practical challenges such as potential training instability and implicit reward bias. To address the challenges, we propose Support-weighted Adversarial Imitation Learning (SAIL), a general framework that extends a given AIL algorithm with information derived from support estimation of the expert policies. SAIL improves the quality of the reinforcement signals by weighing the adversarial reward with a confidence score from support estimation of the expert policy. We also show that SAIL is always at least as efficient as the underlying AIL algorithm that SAIL uses for learning the adversarial reward. Empirically, we show that the proposed method achieves better performance and training stability than baseline methods on a wide range of benchmark control tasks.

Key facts. Cited by 3 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 15 of its 26 references that are in the map. First posted on arXiv 20 Feb 2020.

Builds on

15 of 26 references.

Closest ancestors · 3

Same direction, newest first

  1. 2019Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation16 May
  2. 2019Generative predecessor models for sample-efficient imitation learning1 Apr
  3. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep

Other references · 12

  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2015Trust Region Policy Optimizationcited by 2,503
  4. 2016OpenAI Gymcited by 1,684
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2018Exploration by Random Network Distillationcited by 966
  7. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  8. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  9. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  10. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 167
  11. 2017Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Predictioncited by 93
  12. 2018Nonparametric Density Estimation under Adversarial Lossescited by 26

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1.

3 papers.

  1. 2022You Only Live Once: Single-Life Reinforcement Learningcited by 23
  2. 2024SEABO: A Simple Search-Based Method for Offline Imitation Learningcited by 14
  3. 2025Coupled Distributional Random Expert Distillation for World Model Online Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning
  2. 2026Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
  3. 2020Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations
  4. 2020Off-Policy Adversarial Inverse Reinforcement Learning
  5. 2025SD2AIL: Adversarial Imitation Learning from Synthetic Demonstrations via Diffusion Models
  6. 2026Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
  7. 2024Adversarial Imitation Learning via Boosting
  8. 2022Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis