Mungojerrie: Linear-Time Objectives in Model-Free Reinforcement Learning

被引：2

作者：

Hahn, Ernst Moritz ^{[1
]}

Perez, Mateo ^{[2
]}

Schewe, Sven ^{[3
]}

Somenzi, Fabio ^{[2
]}

Trivedi, Ashutosh ^{[2
]}

Wojtczak, Dominik ^{[3
]}

机构：

[1] Univ Twente, Enschede, Netherlands

[2] Univ Colorado, Boulder, CO 80309 USA

[3] Univ Liverpool, Liverpool, Merseyside, England

来源：

TOOLS AND ALGORITHMS FOR THE CONSTRUCTION AND ANALYSIS OF SYSTEMS, PT I, TACAS 2023 | 2023年 / 13993卷

基金：

欧盟地平线“2020”; 美国国家科学基金会;

关键词：

AUTOMATA;

D O I：

10.1007/978-3-031-30823-9_27

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Mungojerrie is an extensible tool that provides a frame-work to translate linear-time objectives into reward for reinforcement learning (RL). The tool provides convergent RL algorithms for stochastic games, reference implementations of existing reward translations for omega-regular objectives, and an internal probabilistic model checker for omega-regular objectives. This functionality is modular and operates on shared data structures, which enables fast development of new translation techniques. Mungojerrie supports finite models specified in PRISM and omega-automata specified in the HOA format, with an integrated command line interface to external linear temporal logic translators. Mungojerrie is distributed with a set of benchmarks for omega-regular objectives in RL.

引用

页码：527 / 545

页数：19

共 50 条

[1] Model-Free Reinforcement Learning for Stochastic Games with Linear Temporal Logic Objectives
Bozkurt, Alper Kamil
Wang, Yu
Zavlanos, Michael M.
Pajic, Miroslav
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 10649 - 10655
[2] Limit Reachability for Model-Free Reinforcement Learning of ω-Regular Objectives
Hahn, Ernst Moritz
Perez, Mateo
Schewe, Sven
Somenzi, Fabio
Trivedi, Ashutosh
Wojtczak, Dominik
PROCEEDINGS OF THE 5TH INTERNATIONAL WORKSHOP ON SYMBOLIC-NUMERIC METHODS FOR REASONING ABOUT CPS AND IOT (SNR 2019), 2019, : 16 - 18
[3] Omega-Regular Objectives in Model-Free Reinforcement Learning
Hahn, Ernst Moritz
Perez, Mateo
Schewe, Sven
Somenzi, Fabio
Trivedi, Ashutosh
Wojtczak, Dominik
TOOLS AND ALGORITHMS FOR THE CONSTRUCTION AND ANALYSIS OF SYSTEMS, PT I, 2019, 11427 : 395 - 412
[4] Model-Free Reinforcement Learning for Lexicographic Omega-Regular Objectives
Hahn, Ernst Moritz
Perez, Mateo
Schewe, Sven
Somenzi, Fabio
Trivedi, Ashutosh
Wojtczak, Dominik
FORMAL METHODS, FM 2021, 2021, 13047 : 142 - 159
[5] Linear Quadratic Control Using Model-Free Reinforcement Learning
Yaghmaie, Farnaz Adib
Gustafsson, Fredrik
Ljung, Lennart
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (02) : 737 - 752
[6] Poster Abstract: Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives
Balakrishnan, Anand
Jaksic, Stefan
Aguilar, Edgar A.
Nickovic, Dejan
Deshmukh, Jyotirmoy, V
HSCC 2022: PROCEEDINGS OF THE 25TH ACM INTERNATIONAL CONFERENCE ON HYBRID SYSTEMS: COMPUTATION AND CONTROL (PART OF CPS-IOT WEEK 2022), 2022,
[7] Faithful and Effective Reward Schemes for Model-Free Reinforcement Learning of Omega-Regular Objectives
Hahn, Ernst Moritz
Perez, Mateo
Schewe, Sven
Somenzi, Fabio
Trivedi, Ashutosh
Wojtczak, Dominik
AUTOMATED TECHNOLOGY FOR VERIFICATION AND ANALYSIS (ATVA 2020), 2020, 12302 : 108 - 124
[8] Learning Representations in Model-Free Hierarchical Reinforcement Learning
Rafati, Jacob
Noelle, David C.
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 10009 - 10010
[9] Secure Linear Quadratic Regulator Using Sparse Model-Free Reinforcement Learning
Kiumarsi, Bahare
Basar, Tamer
2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC), 2019, : 3641 - 3647
[10] On Model-free Reinforcement Learning for Switched Linear Systems: A Subspace Clustering Approach
Li, Hao
Chen, Hua
Zhang, Wei
2018 56TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2018, : 123 - 130

← 1 2 3 4 5 →