Determination and optimization of reinforcement learning parameters for driver actions in traffic
| Autor: | Linsen Chong, Alejandra Medina, Bryan Higgs, Montasir M Abbas, C. Y. David Yang |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Engineering
Error-driven learning Learning classifier system business.industry Vehicle behavior computer.software_genre Machine learning ComputingMethodologies_ARTIFICIALINTELLIGENCE Emergency situations Vehicle dynamics Intelligent agent Reinforcement learning Artificial intelligence Hyper-heuristic business computer |
| Zdroj: | ITSC |
| DOI: | 10.1109/itsc.2011.6083090 |
| Popis: | An agent-based, artificial intelligence technique known as reinforcement learning has been used to capture vehicle behavior and simulate driver's actions in traffic, especially during emergency situations. This paper discusses the training parameters and their influence on agent simulation performance. A type of agent training technique called Neuro-Fuzzy Actor Critic Reinforcement Learning (NFACRL) is used to test the training parameters with an objective of improving simulation performance. A systematic parameter determination and optimization methodology is provided. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|