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

[21] Policy Learning with Constraints in Model-free Reinforcement Learning: A Survey
Liu, Yongshuai
Halev, Avishai
Liu, Xin
PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4508 - 4515
[22] Improving Optimistic Exploration in Model-Free Reinforcement Learning
Grzes, Marek
Kudenko, Daniel
ADAPTIVE AND NATURAL COMPUTING ALGORITHMS, 2009, 5495 : 360 - 369
[23] Model-Free Preference-Based Reinforcement Learning
Wirth, Christian
Fuernkranz, Johannes
Neumann, Gerhard
THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 2222 - 2228
[24] Constrained model-free reinforcement learning for process optimization
Pan, Elton
Petsagkourakis, Panagiotis
Mowbray, Max
Zhang, Dongda
del Rio-Chanona, Ehecatl Antonio
COMPUTERS & CHEMICAL ENGINEERING, 2021, 154
[25] Model-Free μ Synthesis via Adversarial Reinforcement Learning
Keivan, Darioush
Havens, Aaron
Seiler, Peter
Dullerud, Geir
Hu, Bin
2022 AMERICAN CONTROL CONFERENCE, ACC, 2022, : 3335 - 3341
[26] An adaptive clustering method for model-free reinforcement learning
Matt, A
Regensburger, G
INMIC 2004: 8TH INTERNATIONAL MULTITOPIC CONFERENCE, PROCEEDINGS, 2004, : 362 - 367
[27] Model-Free Reinforcement Learning for Mean Field Games
Mishra, Rajesh
Vasal, Deepanshu
Vishwanath, Sriram
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2023, 10 (04): : 2141 - 2151
[28] Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Mesnard, Thomas
Weber, Theophane
Viola, Fabio
Thakoor, Shantanu
Saade, Alaa
Harutyunyan, Anna
Dabney, Will
Stepleton, Tom
Heess, Nicolas
Guez, Arthur
Moulines, Eric
Hutter, Marcus
Buesing, Lars
Munos, Remi
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[29] Covariance matrix adaptation for model-free reinforcement learning
Adaptation de la matrice de covariance pour l'apprentissage par renforcement direct
2013, Lavoisier, 14 rue de Provigny, Cachan Cedex, F-94236, France (27)
[30] Driving in Dense Traffic with Model-Free Reinforcement Learning
Saxena, Dhruv Mauria
Bae, Sangjae
Nakhaei, Alireza
Fujimura, Kikuo
Likhachev, Maxim
2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 5385 - 5392

← 1 2 3 4 5 →