Adversarial Imitation Learning

Adversarial Imitation Learning (AIL) aims to train agents to mimic expert behavior without explicitly defining a reward function, leveraging the power of adversarial training to learn optimal policies from demonstrations. Current research focuses on improving sample efficiency through off-policy learning and the use of various model architectures, including transformers, diffusion models, and autoencoders, to enhance robustness and scalability across diverse tasks, such as robotic control and autonomous driving. This approach holds significant promise for applications requiring complex behavior learning where reward design is difficult or impossible, offering a powerful alternative to traditional reinforcement learning methods. The development of theoretically grounded algorithms with convergence guarantees and improved exploration strategies are key areas of ongoing investigation.

Papers

October 17, 2024

Diffusing States and Matching Scores: A New Framework for Imitation Learning
Runzhe Wu, Yiding Chen, Gokul Swamy, Kianté Brantley, Wen Sun
LeArning Abstract New Framework Imitation Learning GAN Model Adversarial Learning Feature Imitation Score Matching Adversarial Imitation Learning Adversarial Imitation

October 15, 2024

ILAEDA: An Imitation Learning Based Approach for Automatic Exploratory Data Analysis
Abhijit Manatkar, Devarsh Patel, Hima Patel, Naresh Manwani
Reinforcement Learning Imitation Learning Constructive Approach Adversarial Imitation Learning Exploratory Data Analysis Exploratory Learning EDA Developer

October 8, 2024

Quality Diversity Imitation Learning
Zhenglin Wan, Xingrui Yu, David Mark Bossens, Yueming Lyu, Qing Guo, Flint Xiaofeng Fan, Ivor Tsang
Imitation Learning Inverse Reinforcement Learning Adversarial Imitation Learning Obstacle Scenario

July 16, 2024

Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion
Henri-Jacques Geiß, Firas Al-Hafez, Andre Seyfarth, Jan Peters, Davide Tateo
Action Space Efficient Exploration Action Feature Human Like Locomotion Behavior Bipedal Locomotion Multiple Gait Adversarial Imitation Learning Simulated Humanoid

July 12, 2024

PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization
Yuyang Ye, Lu-An Tang, Haoyu Wang, Runlong Yu, Wenchao Yu, Erhu He, Haifeng Chen, Hui Xiong
Deep Reinforcement Learning System Performance Adversarial Imitation Learning Process Optimization Optimal Operation Carbon Neutrality

May 26, 2024

Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees
Yilei Chen, Vittorio Giammarino, James Queeney, Ioannis Ch. Paschalidis
Sample Complexity Convergence Guarantee Sample Efficiency Adversarial Imitation Learning Policy Adversarial Imitation Learning

April 12, 2024

Adversarial Imitation Learning via Boosting
Jonathan D. Chang, Dhruv Sreenivas, Yingbing Huang, Kianté Brantley, Wen Sun
Actor Critic Adversarial Imitation Learning Policy Algorithm Adversarial Imitation Policy Adversarial Imitation Learning

February 22, 2024

BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplay
Catherine Weaver, Chen Tang, Ce Hao, Kenta Kawamoto, Masayoshi Tomizuka, Wei Zhan
Imitation Learning Autonomous Racing Adversarial Imitation Learning Racing Scenario Behavior Transformer

January 22, 2024

Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits
Yinghui Li, Jinze Wu, Xin Liu, Weizhong Guo, Yufei Xue
High Efficiency Legged Robot Reward Structure Adversarial Imitation Learning Locomotion Policy Biological Learning Hexapod Robot Experiential Learning Robust Gait Motion Robust

January 21, 2024

Visual Imitation Learning with Calibrated Contrastive Representation
Yunke Wang, Linwei Tao, Bo Du, Yutian Lin, Chang Xu
Contrastive Learning Contrastive Loss Agent System Contrastive Representation Learning Adversarial Imitation Learning Visual Imitation Learning

December 11, 2023

DiffAIL: Diffusion Adversarial Imitation Learning
Bingzheng Wang, Guoqiang Wu, Teng Pang, Yan Zhang, Yilong Yin
Reinforcement Learning State Action Pair Adversarial Imitation Learning Adversarial Imitation Demonstration Example

November 14, 2023

Adversarial Imitation Learning On Aggregated Data
Pierre Le Pelletier de Woillemont, Rémi Labory, Vincent Corruble
Reinforcement Learning Optimal Policy Inverse Reinforcement Learning Adversarial Imitation Learning Aggregated Data Linear Reward

September 29, 2023

Adversarial Imitation Learning from Visual Observations using Latent Information
Vittorio Giammarino, James Queeney, Ioannis Ch. Paschalidis
Reinforcement Learning High Dimensional Partial Observability Adversarial Imitation Learning Visual Exploration Latent Topic Policy Adversarial Imitation Learning

September 13, 2023

Dissipative Imitation Learning for Discrete Dynamic Output Feedback Control with Sparse Data Sets
Amy K. Strong, Ethan J. LoCicero, Leila J. Bridgeman
Imitation Learning Sparse Data Discrete Environment Adversarial Imitation Learning Learned Controller Output Feedback

February 13, 2023

Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning
Yunke Wang, Bo Du, Chang Xu
Imitation Learning Expert Demonstration Adversarial Imitation Learning Adversarial Imitation

February 2, 2023

December 30, 2022

Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks
Trevor Ablett, Bryan Chan, Jonathan Kelly
LeArning Abstract Imitation Learning Multi Task Environment Exploration Online Reinforcement Learning State Action Pair Adversarial Imitation Learning Adversarial Imitation

October 20, 2022

Robust Imitation via Mirror Descent Inverse Reinforcement Learning
Dong-Sig Han, Hyunseo Kim, Hyundo Lee, Je-Hwan Ryu, Byoung-Tak Zhang
Inverse Reinforcement Learning Reward Learning Mirror Descent Adversarial Imitation Learning Robust Imitation

October 18, 2022

Planning for Sample Efficient Imitation Learning
Zhao-Heng Yin, Weirui Ye, Qifeng Chen, Yang Gao
Imitation Learning Task Planning Based Imitation Adversarial Imitation Learning Imitation Based