𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Gradient estimation in dendritic reinforcement learning

✍ Scribed by Mathieu Schiess,Robert Urbanczik…


Book ID
115028167
Publisher
BioMed Central
Year
2012
Tongue
English
Weight
360 KB
Volume
2
Category
Article
ISSN
2190-8567

No coin nor oath required. For personal study only.


📜 SIMILAR VOLUMES


Estimation and Approximation Bounds for
✍ Peter L. Bartlett; Jonathan Baxter 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 156 KB

We model reinforcement learning as the problem of learning to control a partially observable Markov decision process (POMDP) and focus on gradient ascent approaches to this problem. In an earlier work (2001, J. Artificial Intelligence Res. 14) we introduced GPOMDP, an algorithm for estimating the pe