Adversarial Inverse Reinforcement Learning

Adversarial Inverse Reinforcement Learning (AIRL) aims to infer an agent's reward function by observing its behavior, often using a generative adversarial network (GAN) framework where a discriminator distinguishes between expert and agent-generated trajectories. Current research focuses on improving AIRL's robustness in stochastic environments, enhancing policy imitation and reward recovery, and applying it to diverse applications like human-robot collaboration and interactive recommendation systems. These advancements are significant because they enable robots to learn complex tasks from human demonstrations, improve the interpretability of deep reinforcement learning models, and offer novel approaches to strategic decision-making in adversarial settings.

Papers

November 11, 2024

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
Arnav Kumar Jain, Harley Wiltzer, Jesse Farebrother, Irina Rish, Glen Berseth, Sanjiban Choudhury
Inverse Reinforcement Learning Reward Model Matching Accuracy Adversarial Game Successor Feature Adversarial Inverse Reinforcement Learning Game Solving

October 10, 2024

Rethinking Adversarial Inverse Reinforcement Learning: From the Angles of Policy Imitation and Transferable Reward Recovery
Yangchun Zhang, Wang Zhou, Yirui Zhou
Proximal Policy Optimization Reinforcement Learning Algorithm Inverse Reinforcement Learning Tilting Angle Policy Actor Critic Imitation Policy Adversarial Inverse Reinforcement Learning

October 4, 2024

Model-Based Reward Shaping for Adversarial Inverse Reinforcement Learning in Stochastic Environments
Simon Sinong Zhan, Qingyuan Wu, Philip Wang, Yixuan Wang, Ruochen Jiao, Chao Huang, Qi Zhu
Reward Shaping Stochastic Environment Adversarial Inverse Reinforcement Learning

April 29, 2024

Socially Adaptive Path Planning Based on Generative Adversarial Network
Yao Wang, Yuqi Kong, Wenzheng Chi, Lining Sun
Generative Adversarial Network Adversarial Inverse Reinforcement Learning Adaptive Path Planning

March 21, 2024

Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof
Yangchun Zhang, Qiang Liu, Weiming Li, Yirui Zhou
Imitation Learning Imitation Policy Adversarial Inverse Reinforcement Learning Equilibrium Computation

February 29, 2024

ARMCHAIR: integrated inverse reinforcement learning and model predictive control for human-robot collaboration
Angelo Caregnato-Neto, Luciano Cavalcante Siebert, Arkady Zgonnikov, Marcos Ricardo Omena de Albuquerque Maximo, Rubens Junqueira Magalhães Afonso
Full Model Predictive Control Human Robot Collaboration Inverse Reinforcement Learning Human Robot Team Adversarial Inverse Reinforcement Learning

January 30, 2024

Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator
Ryoma Furuyama, Daiki Kuyoshi, Satoshi Yamane
Imitation Learning Inverse Reinforcement Learning Bi Discriminator Adversarial Inverse Reinforcement Learning Soft Q Learning

January 5, 2024

Deep Reinforcement Learning for Local Path Following of an Autonomous Formula SAE Vehicle
Harvey Merton, Thomas Delamore, Karl Stol, Henry Williams
Deep Reinforcement Learning Inverse Reinforcement Learning Autonomous Racing Root to Leaf Path Autonomous Driving Stack Adversarial Inverse Reinforcement Learning Formula Student

October 30, 2023

Adversarial Batch Inverse Reinforcement Learning: Learn to Reward from Imperfect Demonstration for Interactive Recommendation
Jialin Liu, Xinyan Su, Zeyu He, Xiangyu Zhao, Jun Li
Reinforcement Learning Inverse Reinforcement Learning Personalized Recommendation Adversarial Inverse Reinforcement Learning Interactive Recommender System Imperfect Demonstration

May 22, 2023

Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
Jiayu Chen, Dipesh Tamboli, Tian Lan, Vaneet Aggarwal
Task Specific Policy Adversarial Inverse Reinforcement Learning Hierarchical Policy Learning

October 20, 2022

How can a Radar Mask its Cognition?
Kunal Pattanayak, Vikram Krishnamurthy, Christopher Berry
Cognitive Learning Adversarial Inverse Reinforcement Learning Adaptive Electronic Counter Counter Measure Cognitive Radar

October 5, 2022

Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control
Jiayu Chen, Tian Lan, Vaneet Aggarwal
Imitation Learning Robot Control Video Demonstration Adversarial Inverse Reinforcement Learning Hierarchical Policy

May 22, 2022

Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement Learner
Kunal Pattanayak, Vikram Krishnamurthy, Christopher Berry
Inverse Reinforcement Learning Strategy Logic Adversarial Inverse Reinforcement Learning

March 30, 2022

Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning
Sean Xie, Soroush Vosoughi, Saeed Hassanpour
Reinforcement Learning Deep Learning Inherent Interpretability Inverse Reinforcement Learning Global Explanation Reinforcement Learning Model Adversarial Inverse Reinforcement Learning

Adversarial Inverse Reinforcement Learning

Papers

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

Rethinking Adversarial Inverse Reinforcement Learning: From the Angles of Policy Imitation and Transferable Reward Recovery

Model-Based Reward Shaping for Adversarial Inverse Reinforcement Learning in Stochastic Environments

Socially Adaptive Path Planning Based on Generative Adversarial Network

Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof

ARMCHAIR: integrated inverse reinforcement learning and model predictive control for human-robot collaboration

Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator

Deep Reinforcement Learning for Local Path Following of an Autonomous Formula SAE Vehicle

Adversarial Batch Inverse Reinforcement Learning: Learn to Reward from Imperfect Demonstration for Interactive Recommendation

Multi-task Hierarchical Adversarial Inverse Reinforcement Learning

How can a Radar Mask its Cognition?

Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control

Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement Learner

Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning