官术网_书友最值得收藏!

Preface

This book brings human-level performance into your applications using the algorithms and techniques of reinforcement learning coupled with Keras, the fast experimental library. Some of the projects that are covered are a delivery vehicle routing application, forecasting stock market prices, a robot control system, a optimal portfolio selection, and the dynamic modeling of a Segway. Throughout this book, you will get your hands dirty with the most popular algorithms, such as the Markov Decision Process, the Monte Carlo method, and Q-learning, so that you can be equipped with complex statistics to get better results.

主站蜘蛛池模板: 星座| 孙吴县| 开阳县| 涿鹿县| 攀枝花市| 正蓝旗| 闽侯县| 山东| 兴和县| 封丘县| 蒲江县| 永定县| 甘德县| 扶绥县| 武乡县| 府谷县| 仪陇县| 黄山市| 政和县| 灵丘县| 都匀市| 四川省| 上饶市| 通州区| 陇川县| 万荣县| 郁南县| 滁州市| 宜川县| 五华县| 衡水市| 平凉市| 皮山县| 达孜县| 突泉县| 桃园市| 福海县| 鹰潭市| 陵川县| 仁化县| 临夏市|