Joy, distress, hope, and fear in reinforcement learning

Elmer Jacobs; Joost Broekens; Catholijn Jonker

Joy, distress, hope, and fear in reinforcement learning

Elmer Jacobs
, Joost Broekens
, Catholijn Jonker

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

In this paper we present a mapping between joy, distress, hope and fear, and Reinforcement Learning primitives. Joy / distress is a signal that is derived from the RL update signal, while hope/fear is derived from the utility of the current state. Agent-based simulation experiments replicate psychological and behavioral dynamics of emotion including: joy and distress reactions that develop prior to hope and fear; fear extinction; habituation of joy; and, task randomness that increases the intensity of joy and distress. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework - coupling it to the literature on habituation, development, and extinction.

Original language	English
Title of host publication	13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
Publisher	International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages	1615-1616
ISBN (Electronic)	9781634391313
Publication status	Published - 2014
Externally published	Yes
Event	13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 - Paris, France Duration: 5 May 2014 → 9 May 2014

Conference

Conference	13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014
Country/Territory	France
City	Paris
Period	5/05/14 → 9/05/14

Persistent URL (handle)

Persistent link

Cite this

@inproceedings{e51740b15b6b40578839905d50946e38,

title = "Joy, distress, hope, and fear in reinforcement learning",

abstract = "In this paper we present a mapping between joy, distress, hope and fear, and Reinforcement Learning primitives. Joy / distress is a signal that is derived from the RL update signal, while hope/fear is derived from the utility of the current state. Agent-based simulation experiments replicate psychological and behavioral dynamics of emotion including: joy and distress reactions that develop prior to hope and fear; fear extinction; habituation of joy; and, task randomness that increases the intensity of joy and distress. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework - coupling it to the literature on habituation, development, and extinction.",

author = "Elmer Jacobs and Joost Broekens and Catholijn Jonker",

year = "2014",

language = "English",

pages = "1615--1616",

booktitle = "13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014",

publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

note = "13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 ; Conference date: 05-05-2014 Through 09-05-2014",

}

Jacobs, E, Broekens, J & Jonker, C 2014, Joy, distress, hope, and fear in reinforcement learning. in 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), pp. 1615-1616, 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014, Paris, France, 5/05/14.

Joy, distress, hope, and fear in reinforcement learning. / Jacobs, Elmer; Broekens, Joost; Jonker, Catholijn.
13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2014. p. 1615-1616.

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Joy, distress, hope, and fear in reinforcement learning

AU - Jacobs, Elmer

AU - Broekens, Joost

AU - Jonker, Catholijn

PY - 2014

Y1 - 2014

N2 - In this paper we present a mapping between joy, distress, hope and fear, and Reinforcement Learning primitives. Joy / distress is a signal that is derived from the RL update signal, while hope/fear is derived from the utility of the current state. Agent-based simulation experiments replicate psychological and behavioral dynamics of emotion including: joy and distress reactions that develop prior to hope and fear; fear extinction; habituation of joy; and, task randomness that increases the intensity of joy and distress. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework - coupling it to the literature on habituation, development, and extinction.

AB - In this paper we present a mapping between joy, distress, hope and fear, and Reinforcement Learning primitives. Joy / distress is a signal that is derived from the RL update signal, while hope/fear is derived from the utility of the current state. Agent-based simulation experiments replicate psychological and behavioral dynamics of emotion including: joy and distress reactions that develop prior to hope and fear; fear extinction; habituation of joy; and, task randomness that increases the intensity of joy and distress. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework - coupling it to the literature on habituation, development, and extinction.

UR - https://www.scopus.com/pages/publications/84911369211

M3 - Conference contribution

SP - 1615

EP - 1616

BT - 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

T2 - 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014

Y2 - 5 May 2014 through 9 May 2014

ER -

Joy, distress, hope, and fear in reinforcement learning

Abstract

Conference

Persistent URL (handle)

Other files and links

Fingerprint

Cite this