https://github.com/codelixir/value-iteration
Understanding Markov Decision Processes using Value Iteration algorithm. For MDL course, Spring 2021.
https://github.com/codelixir/value-iteration
Last synced: 3 months ago
JSON representation
Understanding Markov Decision Processes using Value Iteration algorithm. For MDL course, Spring 2021.
- Host: GitHub
- URL: https://github.com/codelixir/value-iteration
- Owner: codelixir
- Created: 2021-05-08T10:11:32.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-05-08T10:14:33.000Z (over 4 years ago)
- Last Synced: 2025-04-02T09:13:39.880Z (10 months ago)
- Language: Python
- Size: 1.22 MB
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
[](https://forthebadge.com)
#### Contributors
[Dhruvee Birla](https://github.com/dhruvxx) and myself.
This assignment was done as a part of the Machine, Data and Learning course, Spring 2021.
---
# Value Iteration
The goal of this exercise is to understand Markov Decision Processes using the Value Iteration algorithm.
The problem statements have been mentioned in [Assignment.pdf](https://github.com/codelixir/value-iteration/blob/main/Assignment.pdf). Task 2 is similar to Task 1, but with the subtasks having a very little variation from the problem in Task 1.
The [notebook](https://github.com/codelixir/value-iteration/blob/main/valueiteration.ipynb) has the code for the main task (Task 1). The scripts for each task are in the [code](https://github.com/codelixir/value-iteration/tree/main/code) directory, with each file having a variation of a small number of lines from each other. The trace files generated from these scripts are stored in [outputs](https://github.com/codelixir/value-iteration/tree/main/outputs). The [report](https://github.com/codelixir/value-iteration/tree/main/report) analyses the algorithm, our approach and the outputs.