Online Inverse Reinforcement Learning Under Occlusion

被引：0

作者：

Arora, Saurabh ^{[1
]}

Doshi, Prashant ^{[1
]}

Banerjee, Bikramjit ^{[2
]}

机构：

[1] Univ Georgia, Dept Comp Sci, THINC Lab, Athens, GA 30602 USA

[2] Univ Southern Mississippi, Sch Comp Sci & Comp Engn, Hattiesburg, MS 39406 USA

来源：

AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS | 2019年

基金：

美国国家科学基金会;

关键词：

Robot Learning; Online Learning; Robotics; Reinforcement Learning; Inverse Reinforcement Learning;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from observing its behavior on a task. While this problem is witnessing sustained attention, the related problem of online IRL where the observations are incrementally accrued, yet the real-time demands of the application often prohibit a full rerun of an IRL method has received much less attention. We introduce a formal framework for online IRL, called incremental IRL (12RL), and a new method that advances maximum entropy IRL with hidden variables, to this setting. Our analysis shows that the new method has a monotonically improving performance with more demonstration data, as well as probabilistically bounded error, both under full and partial observability. Experiments in a simulated robotic application, which involves learning under occlusion, show the significantly improved performance of 12RL as compared to both batch IRL and an online imitation learning method.

引用

页码：1170 / 1178

页数：9

共 50 条

[21] Robust Inverse Constrained Reinforcement Learning under Model Misspecification
Xu, Sheng
Liu, Guiliang
[J]. Proceedings of Machine Learning Research, 2024, 235 : 55162 - 55185
[22] Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
Viano, Luca
Huang, Yu-Ting
Kamalaruban, Parameswaran
Weller, Adrian
Cevher, Volkan
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[23] Continuous Deep Maximum Entropy Inverse Reinforcement Learning using online POMDP
Silva, Junior A. R.
Grassi Jr, Valdir
Wolf, Denis Fernando
[J]. 2019 19TH INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS (ICAR), 2019, : 382 - 387
[24] Inverse Reinforcement Learning of Behavioral Models for Online-Adapting Navigation Strategies
Herman, Michael
Fiseher, Volker
Gindele, Tobias
Burgard, Wolfram
[J]. 2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2015, : 3215 - 3222
[25] Attention control with reinforcement learning for face recognition under partial occlusion
Ehsan Norouzi
Majid Nili Ahmadabadi
Babak Nadjar Araabi
[J]. Machine Vision and Applications, 2011, 22 : 337 - 348
[26] Attention control with reinforcement learning for face recognition under partial occlusion
Norouzi, Ehsan
Ahmadabadi, Majid Nili
Araabi, Babak Nadjar
[J]. MACHINE VISION AND APPLICATIONS, 2011, 22 (02) : 337 - 348
[27] Remote Sensing Object Tracking With Deep Reinforcement Learning Under Occlusion
Cui, Yanyu
Hou, Biao
Wu, Qian
Ren, Bo
Wang, Shuang
Jiao, Licheng
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[28] Repeated Inverse Reinforcement Learning
Amin, Kareem
Jiang, Nan
Singh, Satinder
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[29] Cooperative Inverse Reinforcement Learning
Hadfield-Menell, Dylan
Dragan, Anca
Abbeel, Pieter
Russell, Stuart
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
[30] Misspecification in Inverse Reinforcement Learning
Skalse, Joar
Abate, Alessandro
[J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 12, 2023, : 15136 - 15143

← 1 2 3 4 5 →