Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic
| Autor: | Kikuo Fujimura, Mykel J. Kochenderfer, Alireza Nakhaei, David Isele, Maxime Bouton |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
business.industry Computer science Computer Science - Artificial Intelligence Cognition 010103 numerical & computational mathematics 010501 environmental sciences 01 natural sciences Task (project management) Variety (cybernetics) Computer Science - Robotics Artificial Intelligence (cs.AI) Reinforcement learning Artificial intelligence 0101 mathematics business Game theory Robotics (cs.RO) 0105 earth and related environmental sciences |
| Zdroj: | ITSC |
| DOI: | 10.48550/arxiv.2005.11895 |
| Popis: | Maneuvering in dense traffic is a challenging task for autonomous vehicles because it requires reasoning about the stochastic behaviors of many other participants. In addition, the agent must achieve the maneuver within a limited time and distance. In this work, we propose a combination of reinforcement learning and game theory to learn merging behaviors. We design a training curriculum for a reinforcement learning agent using the concept of level-$k$ behavior. This approach exposes the agent to a broad variety of behaviors during training, which promotes learning policies that are robust to model discrepancies. We show that our approach learns more efficient policies than traditional training methods. Comment: 6pages, 5 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|