Emergence of emotional appraisal signals in reinforcement learning agents
| LEADER | caa a22 4500 | ||
|---|---|---|---|
| 001 | 605514771 | ||
| 003 | CHVBK | ||
| 005 | 20210128100706.0 | ||
| 007 | cr unu---uuuuu | ||
| 008 | 210128e20150701xx s 000 0 eng | ||
| 024 | 7 | 0 | |a 10.1007/s10458-014-9262-4 |2 doi |
| 035 | |a (NATIONALLICENCE)springer-10.1007/s10458-014-9262-4 | ||
| 245 | 0 | 0 | |a Emergence of emotional appraisal signals in reinforcement learning agents |h [Elektronische Daten] |c [Pedro Sequeira, Francisco Melo, Ana Paiva] |
| 520 | 3 | |a The positive impact of emotions in decision-making has long been established in both natural and artificial agents. In the perspective of appraisal theories, emotions complement perceptual information, coloring our sensations and guiding our decision-making. However, when designing autonomous agents, is emotional appraisal the best complement to the perceptions? Mechanisms investigated in affective neuroscience provide support for this hypothesis in biological agents. In this paper, we look for similar support in artificial systems. We adopt the intrinsically motivated reinforcement learning framework to investigate different sources of information that can guide decision-making in learning agents, and an evolutionary approach based on genetic programming to identify a small set of such sources that have the largest impact on the performance of the agent in different tasks, as measured by an external evaluation signal. We then show that these sources of information: (i) are applicable in a wider range of environments than those where the agents evolved; (ii) exhibit interesting correspondences to emotional appraisal-like signals previously proposed in the literature, pointing towards our departing hypothesis that the appraisal process might indeed provide essential information to complement perceptual capabilities and thus guide decision-making. | |
| 540 | |a The Author(s), 2014 | ||
| 690 | 7 | |a Emotions |2 nationallicence | |
| 690 | 7 | |a Appraisal theory |2 nationallicence | |
| 690 | 7 | |a Intrinsic motivation |2 nationallicence | |
| 690 | 7 | |a Genetic programming |2 nationallicence | |
| 690 | 7 | |a Reinforcement learning |2 nationallicence | |
| 700 | 1 | |a Sequeira |D Pedro |u INESC-ID/Instituto Superior Técnico, Universidade de Lisboa, TagusPark, Edifício IST, 2744-016, Porto Salvo, Portugal |4 aut | |
| 700 | 1 | |a Melo |D Francisco |u INESC-ID/Instituto Superior Técnico, Universidade de Lisboa, TagusPark, Edifício IST, 2744-016, Porto Salvo, Portugal |4 aut | |
| 700 | 1 | |a Paiva |D Ana |u INESC-ID/Instituto Superior Técnico, Universidade de Lisboa, TagusPark, Edifício IST, 2744-016, Porto Salvo, Portugal |4 aut | |
| 773 | 0 | |t Autonomous Agents and Multi-Agent Systems |d Springer US; http://www.springer-ny.com |g 29/4(2015-07-01), 537-568 |x 1387-2532 |q 29:4<537 |1 2015 |2 29 |o 10458 | |
| 856 | 4 | 0 | |u https://doi.org/10.1007/s10458-014-9262-4 |q text/html |z Onlinezugriff via DOI |
| 898 | |a BK010053 |b XK010053 |c XK010000 | ||
| 900 | 7 | |a Metadata rights reserved |b Springer special CC-BY-NC licence |2 nationallicence | |
| 908 | |D 1 |a research-article |2 jats | ||
| 949 | |B NATIONALLICENCE |F NATIONALLICENCE |b NL-springer | ||
| 950 | |B NATIONALLICENCE |P 856 |E 40 |u https://doi.org/10.1007/s10458-014-9262-4 |q text/html |z Onlinezugriff via DOI | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Sequeira |D Pedro |u INESC-ID/Instituto Superior Técnico, Universidade de Lisboa, TagusPark, Edifício IST, 2744-016, Porto Salvo, Portugal |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Melo |D Francisco |u INESC-ID/Instituto Superior Técnico, Universidade de Lisboa, TagusPark, Edifício IST, 2744-016, Porto Salvo, Portugal |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Paiva |D Ana |u INESC-ID/Instituto Superior Técnico, Universidade de Lisboa, TagusPark, Edifício IST, 2744-016, Porto Salvo, Portugal |4 aut | ||
| 950 | |B NATIONALLICENCE |P 773 |E 0- |t Autonomous Agents and Multi-Agent Systems |d Springer US; http://www.springer-ny.com |g 29/4(2015-07-01), 537-568 |x 1387-2532 |q 29:4<537 |1 2015 |2 29 |o 10458 | ||