Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function (Q1886590)
From MaRDI portal
| This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function |
scientific article; zbMATH DE number 2116578
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function |
scientific article; zbMATH DE number 2116578 |
Statements
Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function (English)
0 references
18 November 2004
0 references
Internal prediction
0 references
Reliability
0 references
Model-free reinforcement learning
0 references
TD learning
0 references
Discount rate
0 references
Exploration-exploitation balance
0 references
Temperature parameter
0 references
Meta-learning
0 references
0 references
0 references
0 references
0.6809834837913513
0 references
0.6791847348213196
0 references
0.6717996597290039
0 references
0.6714669466018677
0 references