Name
Abstract | ||
|---|---|---|
In general, a reinforcement learning agent requires many trials in order to find a successful policy in a domain. In this paper we investigate inducing a transition model to reduce the number of trials required by an agent.We discuss an approach that incorporates transition model learning within a contemporary agent design. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/AAMAS.2004.144 | AAMAS |
Keywords | Field | DocType |
transition model,learning rate,successful policy,contemporary agent design,mathematical models,reinforcement learning,decision trees,dynamic programming,multi agent systems,computational complexity,feedback,intelligent agents,approximation theory,computer science,regression analysis | Dynamic programming,Decision tree,Permission,Intelligent agent,Computer science,Multi-agent system,Artificial intelligence,Machine learning,Reinforcement learning,Model learning,Computational complexity theory | Conference |
ISBN | Citations | PageRank |
1-58113-864-4 | 3 | 0.45 |
References | Authors | |
4 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Robert Bridle | 1 | 31 | 2.85 |
| Eric McCreath | 2 | 132 | 14.64 |