Facial feedback for reinforcement learning: A case study and ofine analysis using the TAMER framework
buir.contributor.author | Dibeklioğlu, Hamdi | |
dc.citation.issueNumber | 1 | en_US |
dc.citation.spage | 22 | en_US |
dc.citation.volumeNumber | 34 | en_US |
dc.contributor.author | Li, G. | en_US |
dc.contributor.author | Dibeklioğlu, Hamdi | en_US |
dc.contributor.author | Whiteson, S. | en_US |
dc.contributor.author | Hung, H. | en_US |
dc.date.accessioned | 2021-02-27T16:59:34Z | |
dc.date.available | 2021-02-27T16:59:34Z | |
dc.date.issued | 2020-02 | |
dc.department | Department of Computer Engineering | en_US |
dc.description.abstract | Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this article, we investigate the potential of agent learning from trainers’ facial expressions via interpreting them as evaluative feedback. To do so, we implemented TAMER which is a popular interactive reinforcement learning method in a reinforcement-learning benchmark problem—Infinite Mario, and conducted the first large-scale study of TAMER involving 561 participants. With designed CNN–RNN model, our analysis shows that telling trainers to use facial expressions and competition can improve the accuracies for estimating positive and negative feedback using facial expressions. In addition, our results with a simulation experiment show that learning solely from predicted feedback based on facial expressions is possible and using strong/effective prediction models or a regression method, facial responses would significantly improve the performance of agents. Furthermore, our experiment supports previous studies demonstrating the importance of bi-directional feedback and competitive elements in the training interface. | en_US |
dc.description.provenance | Submitted by Evrim Ergin (eergin@bilkent.edu.tr) on 2021-02-27T16:59:34Z No. of bitstreams: 1 Facial_feedback_for_reinforcement_learning_A_case_study_and_ofine_analysis_using_the_TAMER_framework.pdf: 1828268 bytes, checksum: 787d749849bbf396fb9d1d992700aa8f (MD5) | en |
dc.description.provenance | Made available in DSpace on 2021-02-27T16:59:34Z (GMT). No. of bitstreams: 1 Facial_feedback_for_reinforcement_learning_A_case_study_and_ofine_analysis_using_the_TAMER_framework.pdf: 1828268 bytes, checksum: 787d749849bbf396fb9d1d992700aa8f (MD5) Previous issue date: 2020-02 | en |
dc.identifier.doi | 10.1007/s10458-020-09447-w | en_US |
dc.identifier.issn | 1387-2532 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/75626 | en_US |
dc.language.iso | English | en_US |
dc.publisher | Springer | en_US |
dc.relation.isversionof | https://dx.doi.org/10.1007/s10458-020-09447-w | en_US |
dc.source.title | Autonomous Agents and Multi-Agent Systems | en_US |
dc.subject | Reinforcement learning | en_US |
dc.subject | Facial expressions | en_US |
dc.subject | Human agent interaction | en_US |
dc.subject | Interactive reinforcement learning | en_US |
dc.title | Facial feedback for reinforcement learning: A case study and ofine analysis using the TAMER framework | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Facial_feedback_for_reinforcement_learning_A_case_study_and_ofine_analysis_using_the_TAMER_framework.pdf
- Size:
- 1.74 MB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: