Maximizing learning progress: An internal reward system for development

被引：0
|
作者：
Kaplan, F [1 ]
Oudeyer, PY [1 ]
机构：
[1] Sony Comp Sci Lab Paris, Dev Robot Grp, F-75005 Paris, France
来源：
EMBODIED ARTIFICIAL INTELLIGENCE | 2004年 / 3139卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This chapter presents a generic internal reward system that drives an agent to increase the complexity of its behavior. This reward system does not reinforce a predefined task. Its purpose is to drive the agent to progress in learning given its embodiment and the environment in which it is placed. The dynamics created by such a system are studied first in a simple environment and then in the context of active vision.
引用
收藏
页码：259 / 270
页数：12
相关论文
共 50 条
  • [21] Effective Reward Function in Discernment Behavior Reinforcement Learning based on Categorization Progress
    Kim, Chyon Hae
    Kon, Yusuke
    Navarro, Ricardo
    Gouko, Manabu
    Kobayashi, Yuichi
    2016 IEEE-RAS 16TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS), 2016, : 300 - 305
  • [22] Dynamic-cost-reward connection admission control for maximizing system reward in 4G wireless multihop relaying networks
    Chang, Ben-Jye
    Liang, Ying-Hsin
    Lee, Yu-Hsien
    COMPUTER NETWORKS, 2013, 57 (13) : 2643 - 2655
  • [23] Documenting the Progress of the System Development
    Plaska, Marta
    Walden, Marina
    Snook, Colin
    METHODS, MODELS AND TOOLS FOR FAULT TOLERANCE, 2009, 5454 : 251 - +
  • [24] MULTIAGENT LEARNING FOR BLACK BOX SYSTEM REWARD FUNCTIONS
    Tumer, Kagan
    Agogino, Adrian
    ADVANCES IN COMPLEX SYSTEMS, 2009, 12 (4-5): : 475 - 492
  • [25] CHALLENGES AND PROGRESS IN FACULTY DEVELOPMENT IN GENERAL INTERNAL MEDICINE
    Hemrajani, Reena H.
    Malik, Manpreet S.
    Paletta-Hobbs, Laura E.
    JOURNAL OF GENERAL INTERNAL MEDICINE, 2016, 31 : S868 - S868
  • [26] Work in Progress: Maximizing Model Accuracy in Real-time and Iterative Machine Learning
    Han, Rui
    Zhang, Fan
    Chen, Lydia Y.
    Zhan, Jianfeng
    2017 IEEE REAL-TIME SYSTEMS SYMPOSIUM (RTSS), 2017, : 351 - 353
  • [27] Maximizing the reward in the relocation problem with generalized due dates
    Lin, B. M. T.
    Liu, S. T.
    INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2008, 115 (01) : 55 - 63
  • [28] A UTILITY-MAXIMIZING MECHANISM FOR VICARIOUS REWARD - COMMENTS
    AINSLIE, G
    RATIONALITY AND SOCIETY, 1995, 7 (04) : 393 - 403
  • [29] Maximizing Performance: Augmented Feedback, Focus of Attention, and/or Reward?
    Waelchli, Michael
    Ruffieux, Jan
    Bourquin, Yann
    Keller, Martin
    Taube, Wolfgang
    MEDICINE & SCIENCE IN SPORTS & EXERCISE, 2016, 48 (04) : 714 - 719
  • [30] REWARD AND AFTEREFFECTS OF REWARD IN LEARNING OF GOLDFISH
    MACKINTOSH, NJ
    JOURNAL OF COMPARATIVE AND PHYSIOLOGICAL PSYCHOLOGY, 1971, 76 (02) : 225 - +
12345