Reinforcement learning with augmented states in partially expectation and action observable environment

被引：0

作者：

Guirnaldo, SA ^{[1
]}

Watanabe, K ^{[1
]}

Izumi, K ^{[1
]}

Kiguchi, K ^{[1
]}

机构：

[1] Saga Univ, Fac Engn Syst & Technol, Grad Sch Sci & Engn, Saga 8408502, Japan

来源：

SICE 2002: PROCEEDINGS OF THE 41ST SICE ANNUAL CONFERENCE, VOLS 1-5 | 2002年

关键词：

partially observable Markov decision processes; expectation; reinforcement learning; perception; perceptual aliasing;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The problem of developing good or optimal policies for partially observable Markov decision processes (POMDP) remains one of the most alluring areas of research in artificial intelligence. Encourage by the way how we (humans) form expectations from past experiences and how our decisions and behaviour are affected with our expectations, this paper proposes a method called expectation and action augmented states (EAAS) in reinforcement learning aimed to discover good or near optimal policies in partially observable environment. The method uses the concept of expectation to give distinction between aliased states. It works by augmenting the agent's observation with its expectation of that observation. Two problems from the literature were used to test the proposed method. The results show promising characteristics of the method as compared to some methods currently being used in this domain.

引用

页码：823 / 828

页数：6

共 50 条

[21] A Reinforcement Learning Approach for Solving the Mean Variance Customer Portfolio in Partially Observable Models
Asiain, Erick
Clempner, Julio B.
Poznyak, Alexander S.
[J]. INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2018, 27 (08)
[22] Benefits of Combining Dimensional Attention and Working Memory for Partially Observable Reinforcement Learning Problems
Omatu, Ngozi
Phillips, Joshua L.
[J]. ACMSE 2021: PROCEEDINGS OF THE 2021 ACM SOUTHEAST CONFERENCE, 2021, : 209 - 213
[23] Abstraction in Model Based Partially Observable Reinforcement Learning using Extended Sequence Trees
Cilden, Erkin
Polat, Faruk
[J]. 2012 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE AND INTELLIGENT AGENT TECHNOLOGY (WI-IAT 2012), VOL 2, 2012, : 348 - 355
[24] Deep Recurrent Reinforcement Learning for Partially Observable User Association in a Vertical Heterogenous Network
Khoshkbari, Hesam
Kaddoum, Georges
[J]. IEEE COMMUNICATIONS LETTERS, 2023, 27 (12) : 3235 - 3239
[25] Learning what to memorize: Using intrinsic motivation to form useful memory in partially observable reinforcement learning
Demir, Alper
[J]. APPLIED INTELLIGENCE, 2023, 53 (16) : 19074 - 19092
[26] Learning what to memorize: Using intrinsic motivation to form useful memory in partially observable reinforcement learning
Alper Demir
[J]. Applied Intelligence, 2023, 53 : 19074 - 19092
[27] A gradient-based reinforcement learning approach to dynamic pricing in partially-observable environments
Vengerov, David
[J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2008, 24 (07): : 687 - 693
[28] Reinforcement Learning for Partially Observable Linear Gaussian Systems Using Batch Dynamics of Noisy Observations
Yaghmaie, Farnaz Adib
Modares, Hamidreza
Gustafsson, Fredrik
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2024, 69 (09) : 6397 - 6404
[29] CHQ: A multi-agent reinforcement learning scheme for partially observable Markov decision processes
Osada, H
Fujita, S
[J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2005, E88D (05): : 1004 - 1011
[30] Reinforcement learning with internal expectation for the random neural network
Halici, U
[J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2000, 126 (02) : 288 - 307

← 1 2 3 4 5 →