What's a good prediction? Challenges in evaluating an agent's knowledge.
| Autor: | Kearney A; Department of Computing Science, University of Alberta, Edmonton, AB, Canada.; DeepMind, Edmonton, AB, Canada., Koop AJ; Department of Computing Science, University of Alberta, Edmonton, AB, Canada., Pilarski PM; Department of Computing Science, University of Alberta, Edmonton, AB, Canada.; DeepMind, Edmonton, AB, Canada.; Department of Medicine, University of Alberta, Edmonton, AB, Canada.; Alberta Machine Intelligence Institute, Edmonton, AB, Canada. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Adaptive behavior [Adapt Behav] 2023 Jun; Vol. 31 (3), pp. 197-212. Date of Electronic Publication: 2022 Jun 09. |
| DOI: | 10.1177/10597123221095880 |
| Abstrakt: | Constructing general knowledge by learning task-independent models of the world can help agents solve challenging problems. However, both constructing and evaluating such models remain an open challenge. The most common approaches to evaluating models is to assess their accuracy with respect to observable values. However, the prevailing reliance on estimator accuracy as a proxy for the usefulness of the knowledge has the potential to lead us astray. We demonstrate the conflict between accuracy and usefulness through a series of illustrative examples including both a thought experiment and an empirical example in Minecraft, using the General Value Function framework (GVF). Having identified challenges in assessing an agent's knowledge, we propose an alternate evaluation approach that arises naturally in the online continual learning setting: we recommend evaluation by examining internal learning processes, specifically the relevance of a GVF's features to the prediction task at hand. This paper contributes a first look into evaluation of predictions through their use, an integral component of predictive knowledge which is as of yet unexplored. Competing Interests: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article. (© The Author(s) 2022.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|