Generative Adversarial Imitation Learning

Generative Adversarial Imitation Learning (GAIL) is a machine learning technique that enables agents to learn complex behaviors by imitating expert demonstrations without explicit reward functions. Current research focuses on improving GAIL's stability and efficiency, often through integrating techniques like diffusion models to refine reward signals, control theory to stabilize training, and hierarchical architectures to handle high-dimensional data. These advancements are enhancing GAIL's applicability across diverse fields, including robotics (e.g., autonomous navigation, manipulation), virtual character animation, and even cybersecurity (e.g., penetration testing), demonstrating its significant impact on both theoretical understanding and practical applications.

Papers

June 24, 2024

RaCIL: Ray Tracing based Multi-UAV Obstacle Avoidance through Composite Imitation Learning
Harsh Bansal, Vyom Goyal, Bhaskar Joshi, Akhil Gupta, Harikumar Kandath
Imitation Learning Unmanned Aerial Vehicle Collision Avoidance Obstacle Avoidance Proximal Policy Optimization Ray Tracing Generative Adversarial Imitation Learning

May 25, 2024

Diffusion-Reward Adversarial Imitation Learning
Chun-Mao Lai, Hsiang-Chun Wang, Ping-Chun Hsieh, Yu-Chiang Frank Wang, Min-Hung Chen, Shao-Hua Sun
Diffusion Model Policy Learning Generative Training Generative Adversarial Imitation Learning

February 26, 2024

C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
Tianjiao Luo, Tim Pearce, Huayu Chen, Jianfei Chen, Jun Zhu
GAN Model Policy Reinforcement Learning Generative Training Generative Adversarial Imitation Learning Control Theory Generative Adversarial Imitation

January 28, 2024

Harnessing Network Effect for Fake News Mitigation: Selecting Debunkers via Self-Imitation Learning
Xiaofei Xu, Ke Deng, Michael Dann, Xiuzhen Zhang
Generative Adversarial Imitation Learning Network Effect

December 18, 2023

Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective
Wanying Wang, Yichen Zhu, Yirui Zhou, Chaomin Shen, Jian Tang, Zhiyuan Xu, Yaxin Peng, Yangchun Zhang
Imitation Learning Bayesian Perspective Generative Adversarial Imitation Learning Imitation Policy

October 12, 2023

Discovering Fatigued Movements for Virtual Character Animation
Noshaba Cheema, Rui Xu, Nam Hee Kim, Perttu Hämäläinen, Vladislav Golyanik, Marc Habermann, Christian Theobalt, Philipp Slusallek
Character Animation Fatigue Induced Generative Adversarial Imitation Learning Muscle Fatigue

September 27, 2023

In-Hand Re-grasp Manipulation with Passive Dynamic Actions via Imitation Learning
Dehao Wei, Guokang Sun, Zeyu Ren, Shuang Li, Zhufeng Shao, Xiang Li, Nikos Tsagarakis, Shaohua Ma
Imitation Learning Generative Adversarial Imitation Learning Object Dynamic Motion Controller

August 15, 2023

Generating Personas for Games with Multimodal Adversarial Imitation Learning
William Ahlberg, Alessandro Sestini, Konrad Tollmar, Linus Gisslén
Reinforcement Learning Reward Model Video Game Reward Engineering Generative Adversarial Imitation Learning Persona Knowledge

May 23, 2023

Learning from demonstrations: An intuitive VR environment for imitation learning of construction robots
Kangkang Duan, Zhengbo Zou
Reinforcement Learning LeArning Abstract Imitation Learning Virtual Reality Noisy Demonstration Generative Adversarial Imitation Learning Construction Robot

February 9, 2023

September 21, 2022

Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation
Yoshihisa Tsurumine, Takamitsu Matsubara
Generative Adversarial Imitation Learning Robotic Cloth Manipulation Imperfect Demonstration

September 16, 2022

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
Chenhao Li, Sebastian Blaes, Pavel Kolev, Marin Vlastelica, Jonas Frey, Georg Martius
Skill Discovery Generative Adversarial Imitation Learning Diverse Motion Collaborative Adversarial

June 22, 2022

Latent Policies for Adversarial Imitation Learning
Tianyu Wang, Nikhil Karnwal, Nikolay Atanasov
Action Representation Adversarial Imitation Learning Latent Action Generative Adversarial Imitation Learning Latent Action Space

April 5, 2022

GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning
Jinyin Chen, Shulong Hu, Haibin Zheng, Changyou Xing, Guomin Zhang
Action Space Penetration Testing Generative Adversarial Imitation Learning

March 3, 2022

Fail-Safe Adversarial Generative Imitation Learning
Philipp Geiger, Christoph-Nikolas Straehle
Feature Imitation Generative Adversarial Reachability Analysis Safe Policy Generative Adversarial Imitation Learning

February 12, 2022

Robust Learning from Observation with Model Misspecification
Luca Viano, Yu-Ting Huang, Parameswaran Kamalaruban, Craig Innes, Subramanian Ramamoorthy, Adrian Weller
Imitation Learning Robust Learning Robust Reinforcement Learning Model Misspecification Observation Centric Adversarial Imitation Generative Adversarial Imitation Learning

January 15, 2022

Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets
Mohsen Asgari, Seyed Hossein Khasteh
Deep Reinforcement Learning Proximal Policy Optimization Generative Adversarial Imitation Learning Post Trade Allocation Cryptocurrency Market Strategy Synthesis Reinforcement Learning Solution

Generative Adversarial Imitation Learning

Papers

RaCIL: Ray Tracing based Multi-UAV Obstacle Avoidance through Composite Imitation Learning

Diffusion-Reward Adversarial Imitation Learning

C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory

Harnessing Network Effect for Fake News Mitigation: Selecting Debunkers via Self-Imitation Learning

Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective

Discovering Fatigued Movements for Virtual Character Animation

In-Hand Re-grasp Manipulation with Passive Dynamic Actions via Imitation Learning

Generating Personas for Games with Multimodal Adversarial Imitation Learning

Learning from demonstrations: An intuitive VR environment for imitation learning of construction robots

Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments

Learning to Simulate Daily Activities via Modeling Dynamic Human Needs

Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

Latent Policies for Adversarial Imitation Learning

GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning

Fail-Safe Adversarial Generative Imitation Learning

Robust Learning from Observation with Model Misspecification

Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets