Visual rationalizations in deep reinforcement learning for Atari games
| Autor: | Weitkamp, L., van der Pol, E., Akata, Z., Atzmueller, M., Duivesteijn, W. |
|---|---|
| Přispěvatelé: | Amsterdam Machine Learning lab (IVI, FNWI) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: | |
| Zdroj: | 30th Benelux Conference on Artificial Intelligence: BNAIC 2018 Preproceedings : November 8-9, 2018, Jheronimus Academy of Data Science (JADS), 's-Hertogenbosch, The Netherlands, 315-329 STARTPAGE=315;ENDPAGE=329;TITLE=30th Benelux Conference on Artificial Intelligence Communications in Computer and Information Science ISBN: 9783030319779 BNCAI Artificial Intelligence: 30th Benelux Conference, BNAIC 2018, ‘s-Hertogenbosch, The Netherlands, November 8–9, 2018 : revised selected papers, 151-165 STARTPAGE=151;ENDPAGE=165;TITLE=Artificial Intelligence |
| ISSN: | 1865-0929 |
| Popis: | Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learning models, as other deep learning models, tend to be opaque in their decision-making process. In this work, we propose to make deep reinforcement learning more transparent by visualizing the evidence on which the agent bases its decision. In this work, we emphasize the importance of producing a justification for an observed action, which could be applied to a black-box decision agent. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|