stanford-cs234
所属分类:人工智能/神经网络/深度学习
开发工具:Python
文件大小:72671KB
下载次数:0
上传日期:2019-10-03 12:47:54
上 传 者:
sh-1993
说明: 斯坦福-cs234,斯坦福cs234:强化学习
(stanford-cs234,Stanford CS234 : Reinforcement Learning)
文件列表:
assignments (0, 2019-10-03)
assignments\ass1 (0, 2019-10-03)
assignments\ass1\Makefile (103, 2019-10-03)
assignments\ass1\__MACOSX (0, 2019-10-03)
assignments\ass1\__MACOSX\tex (0, 2019-10-03)
assignments\ass1\__MACOSX\tex\._.DS_Store (120, 2019-10-03)
assignments\ass1\__MACOSX\tex\._Q1.pdf (339, 2019-10-03)
assignments\ass1\__MACOSX\tex\._Q2.pdf (283, 2019-10-03)
assignments\ass1\__MACOSX\tex\._Q3.pdf (283, 2019-10-03)
assignments\ass1\__MACOSX\tex\._assignment1.tex (176, 2019-10-03)
assignments\ass1\assignment1.pdf (218471, 2019-10-03)
assignments\ass1\assignment1_sol.pdf (238147, 2019-10-03)
assignments\ass1\collect_submission.sh (58, 2019-10-03)
assignments\ass1\discrete_env.py (1515, 2019-10-03)
assignments\ass1\frozen_lake.py (4518, 2019-10-03)
assignments\ass1\lake_envs.py (691, 2019-10-03)
assignments\ass1\requirements.txt (35, 2019-10-03)
assignments\ass1\tex (0, 2019-10-03)
assignments\ass1\tex\.DS_Store (6148, 2019-10-03)
assignments\ass1\tex\Q1.pdf (14464, 2019-10-03)
assignments\ass1\tex\Q2.pdf (9635, 2019-10-03)
assignments\ass1\tex\Q3.pdf (9916, 2019-10-03)
assignments\ass1\tex\assignment1.tex (10617, 2019-10-03)
assignments\ass1\vi_and_pi.py (5103, 2019-10-03)
assignments\ass2 (0, 2019-10-03)
assignments\ass2\assignment2.pdf (507499, 2019-10-03)
assignments\ass2\assignment2_sol.pdf (545137, 2019-10-03)
assignments\ass3 (0, 2019-10-03)
assignments\ass3\assignment3.pdf (274955, 2019-10-03)
assignments\ass3\assignment3_sol.pdf (119168, 2019-10-03)
assignments\midterm (0, 2019-10-03)
assignments\midterm\midterm_2017.pdf (205065, 2019-10-03)
assignments\midterm\midterm_2017_sol.pdf (232244, 2019-10-03)
assignments\midterm\midterm_2018.pdf (217175, 2019-10-03)
assignments\midterm\midterm_2018_sol.pdf (200296, 2019-10-03)
notes (0, 2019-10-03)
... ...
# Stanford CS234 : Reinforcement Learning
## Course Description
To realize the dreams and impact of AI requires autonomous systems that learn to
make good decisions. Reinforcement learning is one powerful paradigm for doing
so, and it is relevant to an enormous range of tasks, including robotics, game
playing, consumer modeling and healthcare. This class will provide a solid
introduction to the field of reinforcement learning and students will learn
about the core challenges and approaches, including generalization and
exploration. Through a combination of lectures, and written and coding
assignments, students will become well versed in key ideas and techniques for
RL. Assignments will include the basics of reinforcement learning as well as
deep reinforcement learning ” an extremely promising new area that combines deep
learning techniques with reinforcement learning. In addition, students will
advance their understanding and the field of RL through a final project.
## Learning Outcomes
By the end of the class students should be able to:
Define the key features of reinforcement learning that distinguishes it from AI
and non-interactive machine learning (as assessed by the exam).
Given an application problem (e.g. from computer vision, robotics, etc), decide
if it should be formulated as a RL problem; if yes be able to define it formally
(in terms of the state space, action space, dynamics and reward model), state
what algorithm (from class) is best suited for addressing it and justify your
answer (as assessed by the project and the exam).
Implement in code common RL algorithms (as assessed by the homeworks).
Describe (list and define) multiple criteria for analyzing RL algorithms and
evaluate algorithms on these metrics: e.g. regret, sample complexity,
computational complexity, empirical performance, convergence, etc (as assessed
by homeworks and the exam).
Describe the exploration vs exploitation challenge and compare and contrast at
least two approaches for addressing this challenge (in terms of performance,
scalability, complexity of implementation, and theoretical guarantees) (as
assessed by an assignment and the exam).
### References
* [Course webpage](http://web.stanford.edu/class/cs234/index.html)
* [Youtube
videos](https://www.youtube.com/playlist?list=PLoROMvodv4rOSOPzutgyCTapiGlY2Nd8u)
近期下载者:
相关文件:
收藏者: