Cargando…
Intrinsic Rewards for Maintenance, Approach, Avoidance, and Achievement Goal Types
In reinforcement learning, reward is used to guide the learning process. The reward is often designed to be task-dependent, and it may require significant domain knowledge to design a good reward function. This paper proposes general reward functions for maintenance, approach, avoidance, and achieve...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Frontiers Media S.A.
2018
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6189580/ https://www.ncbi.nlm.nih.gov/pubmed/30356820 http://dx.doi.org/10.3389/fnbot.2018.00063 |