该参考描述所示目录。请向院校确认当前的招生项目及适用于您入学年的条件。
描述
强化学习 多臂赌博机、马尔可夫决策过程、基于模型和无模型方法（如动态规划、蒙特卡洛方法和时序差分方法）用于学习价值函数和策略函数。近似解法包括深度强化学习。讲座，每周3小时。限制：对 COSC 单专业或联合专业、GAME、NEUR 和数据科学项目开放。先修课程：COSC 3P71（最低60%）。注意：本课程可能以多种授课方式提供。授课方式将在学期课程表中列出。
先修课程
- 先修课程：COSC 3P71（最低 60%）。
条件与方式
- 限制：对 COSC 单专业或联合专业、GAME、NEUR 和数据科学项目开放。
- 先修课程：COSC 3P71（最低 60%）。
- 注：本课程可能以多种授课方式开设。授课方式将在适用学期的学术课程表中列出。
原文参考文本
Reinforcement Learning Multi-armed bandits, Markov decision processes, model-based and model-free methods (such as dynamic programming, Monte Carlo methods, and temporal-difference methods) for learning value and policy functions. Approximation solutions including deep reinforcement learning. Lectures, 3 hours per week. Restriction: open to COSC single or combined, GAME, NEUR , and Data Science programs. Prerequisite(s): COSC 3P71 (minimum 60 percent). Note: this course may be offered in multiple modes of delivery. The method of delivery will be listed on the academic timetable, in the applicable term.
- Prerequisite(s): COSC 3P71 (minimum 60 percent).
- Restriction: open to COSC single or combined, GAME, NEUR , and Data Science programs.
- Note: this course may be offered in multiple modes of delivery. The method of delivery will be listed on the academic timetable, in the applicable term.
来源与参考
为帮助您核实信息，保留了日期和来源。为便于阅读提供了翻译；以官方来源为准，查看条件和要求。
来源参考 : https://brocku.ca/webcal/2024/undergrad/cosc.html