Imitation Learned Policy

Imitation learning (IL) aims to train agents by mimicking expert demonstrations, avoiding the need for explicit reward functions. Current research focuses on improving IL's efficiency and robustness, addressing challenges like limited expert data, safety concerns (especially in robotics), and generalization to unseen environments or tasks. This involves developing novel algorithms, such as those incorporating key-state guidance, anomaly detection, and online adaptation, often leveraging techniques from reinforcement learning and incorporating attention mechanisms or privileged knowledge distillation. The resulting advancements have significant implications for various fields, including robotics, autonomous driving, and human-computer interaction, enabling the development of more efficient, safe, and adaptable intelligent systems.

Papers

August 6, 2024

KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance
Jingxian Lu, Wenke Xia, Dong Wang, Zhigang Wang, Bin Zhao, Di Hu, Xuelong Li
Imitation Learning Imitation Learned Policy Conditioned Imitation

July 29, 2024

Detecting Unsafe Behavior in Neural Network Imitation Policies for Caregiving Robotics
Andrii Tytarenko
Robotics Domain Based Policy Neural Network Policy Robotics Benchmark Imitation Learned Policy

June 7, 2024

Online Adaptation for Enhancing Imitation Learning Policies
Federico Malato, Ville Hautamaki
Imitation Learning Autonomous Agent Online Adaptation Adaptive Agent Imitation Learned Policy

October 9, 2023

Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments
Xiong-Hui Chen, Junyin Ye, Hang Zhao, Yi-Chen Li, Haoran Shi, Yu-Yan Xu, Zhihao Ye, Si-Hang Yang, Anqi Huang, Kai Xu, Zongzhang Zhang, Yang Yu
Imitation Learning Imitation Policy Imitation Learned Policy Reinforcement Learning Paradigm Imitation Ability Imitator Learning

May 29, 2023

Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective
Haoran He, Peilin Wu, Chenjia Bai, Hang Lai, Lingxiao Wang, Ling Pan, Xiaolin Hu, Weinan Zhang
Reinforcement Learning Privileged Information Imitation Learned Policy Privileged Knowledge Distillation

December 12, 2022

CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning
Zhao Mandi, Homanga Bharadhwaj, Vincent Moens, Shuran Song, Aravind Rajeswaran, Vikash Kumar
New Framework Non Humanoid Robot Robot Learning Large Scale Training Visual Imitation Learning Imitation Learned Policy Cacto Sl Task Scaling

October 15, 2022

A Policy-Guided Imitation Approach for Offline Reinforcement Learning
Haoran Xu, Li Jiang, Jianxiong Li, Xianyuan Zhan
Offline Reinforcement Learning Based Imitation State of the Art Imitation Imitation Learned Policy Reward Maximizing Policy

October 11, 2022

Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning
Anton Bakhtin, David J Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander H Miller, Noam Brown
Multi Agent Task Planning Game Content Regularized Reinforcement Learning Imitation Learned Policy Self Play Reinforcement Learning Reward Maximizing Policy

October 4, 2022

Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field
Yurui Du, Flavia Sofia Acerbo, Jens Kober, Tong Duy Son
LeArning Abstract Autonomous Vehicle Imitation Learning Multi Agent Noisy Demonstration Driver Behavior Imitation Learned Policy Risk Field

August 3, 2022

Sequence Model Imitation Learning with Unobserved Contexts
Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu
Imitation Learning Feature Imitation Policy Reinforcement Learning Unobserved Variable Sub Optimal Expert Level Performance Imitation Learned Policy

December 14, 2021

Modeling Strong and Human-Like Gameplay with KL-Regularized Search
Athul Paul Jacob, David J. Wu, Gabriele Farina, Adam Lerer, Hengyuan Hu, Anton Bakhtin, Jacob Andreas, Noam Brown
Imitation Learning Strong Model Imitation Learned Policy

November 3, 2021

Smooth Imitation Learning via Smooth Costs and Smooth Policies
Sapana Chaudhary, Balaraman Ravindran
Reinforcement Learning Imitation Learning Adversarial Imitation Learning Smooth Convex Imitation Learned Policy