https://github.com/silviatulli/rlhomework
multi-armed bandit, gambler problem, cliff problem and TD learning
https://github.com/silviatulli/rlhomework
cliff-problem gambler-problem multi-armed-bandit sequential-decision-making-problems td-learning
Last synced: 17 days ago
JSON representation
multi-armed bandit, gambler problem, cliff problem and TD learning
- Host: GitHub
- URL: https://github.com/silviatulli/rlhomework
- Owner: Silviatulli
- Created: 2018-12-17T16:57:30.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2021-06-02T16:14:42.000Z (almost 4 years ago)
- Last Synced: 2025-05-01T12:05:24.085Z (17 days ago)
- Topics: cliff-problem, gambler-problem, multi-armed-bandit, sequential-decision-making-problems, td-learning
- Language: Python
- Homepage:
- Size: 17.6 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Reinforcement Learning Homework
These exercises are part of the coursework for [Reinforcement Learning](https://fenix.tecnico.ulisboa.pt/disciplinas/TAIA/2019-2020/1-semestre/sumarios).
You will find the implementation of multi-armed bandit, gambler problem, cliff problem and TD learning.
## Reference Book
[Reinforcement Learning: An Introduction](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf)