Imitation Policy

Imitation learning aims to train agents to mimic expert behavior from observational data, bypassing the need for explicit reward functions. Current research emphasizes improving robustness and generalization of learned policies, focusing on techniques like offline-to-online finetuning, selective imitation from large datasets, and adversarial methods to address compounding errors and gradient explosion issues in algorithms such as behavior cloning and Generative Adversarial Imitation Learning (GAIL). These advancements are crucial for deploying reliable imitation policies in safety-critical applications like robotics and autonomous systems, where generalization to unseen scenarios is paramount.

Papers

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

May 24, 2024

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
Sheng Yue, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, Yaoxue Zhang
Imitation Learning Policy Optimization Offline Imitation Learning Online Fine Tuning Imitation Policy Offline Pre Training

May 6, 2024

Select to Perfect: Imitating desired behavior from large multi-agent data
Tim Franzmeyer, Edith Elkind, Philip Torr, Jakob Foerster, Joao Henriques
Multi Agent AI Agent BEHAVIOR Explanation Imitation Policy Collective Navigation Social Desirability

April 8, 2024

SAFE-GIL: SAFEty Guided Imitation Learning
Yusuf Umut Ciftci, Zeyuan Feng, Somil Bansal
Imitation Learning Behavior Cloning Imitation Policy Interactive Imitation Learning Policy Cloning Safe Deep

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

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

November 2, 2023

Invariant Causal Imitation Learning for Generalizable Policies
Ioana Bica, Daniel Jarrett, Mihaela van der Schaar
Causal Feature Policy Generalization Imitation Policy Qualitative Feature Causal Imitation

October 9, 2023

June 23, 2023

Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
Massimiliano Patacchiola, Mingfei Sun, Katja Hofmann, Richard E. Turner
Reinforcement Learning Fine Tuning Offline Reinforcement Learning Shot Imitation Imitation Policy

April 24, 2023

Efficient Robot Skill Learning with Imitation from a Single Video for Contact-Rich Fabric Manipulation
Shengzeng Huo, Anqing Duan, Lijun Han, Luyin Hu, Hesheng Wang, David Navarro-Alarcon
Action Space Feature Imitation Skill Learning Manipulation Skill Shot Imitation Single Video Imitation Policy

December 7, 2022

Tight Performance Guarantees of Imitator Policies with Continuous Actions
Davide Maran, Alberto Maria Metelli, Marcello Restelli
Behavior Cloning Performance Guarantee Imitation Policy Continuous Action

November 4, 2022

Deconfounding Imitation Learning with Variational Inference
Risto Vuorio, Pim de Haan, Johann Brehmer, Hanno Ackermann, Daniel Dijkman, Taco Cohen
Latent Action Imitation Policy Hierarchical Imitation

April 7, 2022

Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning
Carl Qi, Pieter Abbeel, Aditya Grover
Reinforcement Learning Imitation Learning Inverse Reinforcement Learning Robust Learning Noisy Demonstration Imitation Policy Decision Time Planning

Imitation Policy

Papers

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

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning

Select to Perfect: Imitating desired behavior from large multi-agent data

SAFE-GIL: SAFEty Guided Imitation Learning

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

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

Invariant Causal Imitation Learning for Generalizable Policies

Memory-Consistent Neural Networks for Imitation Learning

Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments

Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation

Efficient Robot Skill Learning with Imitation from a Single Video for Contact-Rich Fabric Manipulation

Tight Performance Guarantees of Imitator Policies with Continuous Actions

Deconfounding Imitation Learning with Variational Inference

Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning