強化学習と自動運転に関する独立研究
An Independent Study of Reinforcement Learning and Autonomous Driving
Q学習・深層Qネットワーク・自動運転への応用を段階的に実装し、報酬関数などの環境設定が学習性能に与える影響を調査した。
著者: Hanzhi Yang
分類: cs.AI, cs.RO
原文アブストラクト
Reinforcement learning has become one of the most trending subjects in the recent decade. It has seen applications in various fields such as robot manipulations, autonomous driving, path planning, computer gaming, etc. We accomplished three tasks during the course of this project. Firstly, we studied the Q-learning algorithm for tabular environments and applied it successfully to an OpenAi Gym environment, Taxi. Secondly, we gained an understanding of and implemented the deep Q-network algorithm for Cart-Pole environment. Thirdly, we also studied the application of reinforcement learning in autonomous driving and its combination with safety check constraints (safety controllers). We trained a rough autonomous driving agent using highway-gym environment and explored the effects of various environment configurations like reward functions on the agent training performance.
