Intra-task Curriculum Learning for Faster Reinforcement Learning in Video Games

被引：0

作者：

du Preez-Wilkinson, Nathaniel ^{[1
]}

Gallagher, Marcus ^{[1
]}

Hu, Xuelei ^{[1
]}

机构：

[1] Univ Queensland, Sch Informat Technol & Elect Engn, Brisbane, Qld 4072, Australia

来源：

AI 2018: ADVANCES IN ARTIFICIAL INTELLIGENCE | 2018年 / 11320卷

关键词：

D O I：

10.1007/978-3-030-03991-2_6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we present a new method for improving reinforcement learning training times under the following two assumptions: (1) we know the conditions under which the environment gives reward; and (2) we can control the initial state of the environment at the beginning of a training episode. Our method, called intra-task curriculum learning, presents the different episode starting states to an agent in order of increasing distance to immediate reward.

引用

页码：65 / 70

页数：6

共 50 条

[1] Parallelization of Reinforcement Learning Algorithms for Video Games
Kopel, Marek
Szczurek, Witold
[J]. INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2021, 2021, 12672 : 195 - 207
[2] Distilling Reinforcement Learning Tricks for Video Games
Kanervisto, Anssi
Scheller, Christian
Schraner, Yanick
Hautamaki, Ville
[J]. 2021 IEEE CONFERENCE ON GAMES (COG), 2021, : 1088 - 1091
[3] Designing a Blended Learning Curriculum in the Development of Video Games
Maria Restrepo, Angela
Figueroa, Pablo
[J]. 2014 IEEE FRONTIERS IN EDUCATION CONFERENCE (FIE), 2014,
[4] Deep Reinforcement Learning for Navigation in AAA Video Games
Alonso, Eloi
Peter, Maxim
Goumard, David
Romoff, Joshua
[J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 2133 - 2139
[5] Using Reinforcement Learning for Load Testing of Video Games
Tufano, Rosalia
Scalabrino, Simone
Pascarella, Luca
Aghajani, Emad
Oliveto, Rocco
Bavota, Gabriele
[J]. 2022 ACM/IEEE 44TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2022), 2022, : 2303 - 2314
[6] Curriculum Learning in Reinforcement Learning
Narvekar, Sanmit
[J]. AAMAS'16: PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS, 2016, : 1528 - 1529
[7] Curriculum Learning in Reinforcement Learning
Narvekar, Sanmit
[J]. PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 5195 - 5196
[8] Reinforcement Learning in Video Games Using Nearest Neighbor Interpolation and Metric Learning
Emigh, Matthew S.
Kriminger, Evan G.
Brockmeier, Austin J.
Principe, Jose C.
Pardalos, Panos M.
[J]. IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES, 2016, 8 (01) : 56 - 66
[9] Learning Task-independent Joint Control for Robotic Manipulators with Reinforcement Learning and Curriculum Learning
Vaehrens, Lars
Alvarez, Daniel Diez
Berger, Ulrich
Bogh, Simon
[J]. 2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA, 2022, : 1250 - 1257
[10] Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning
Narvekar, Sanmit
Sinapov, Jivko
Stone, Peter
[J]. PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2536 - 2542

← 1 2 3 4 5 →