https://github.com/codelixir/pomdp

Understanding POMDP using belief update and the SARSOP solver. For the MDL course, Spring 2021.
https://github.com/codelixir/pomdp

Last synced: 10 days ago
JSON representation

Understanding POMDP using belief update and the SARSOP solver. For the MDL course, Spring 2021.

• Host: GitHub
• URL: https://github.com/codelixir/pomdp
• Owner: codelixir
• Created: 2021-05-08T14:49:07.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2021-05-08T14:51:09.000Z (over 4 years ago)
• Last Synced: 2025-02-08T00:19:16.875Z (12 months ago)
• Size: 696 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
[![forthebadge](https://forthebadge.com/images/badges/contains-technical-debt.svg)](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.

---

# POMDP (Partially Observable MDP)

Here we solve Partially Observable MDP problems.

## Task 1

Deriving belief states after certain actions using [belief updates](https://en.wikipedia.org/wiki/Partially_observable_Markov_decision_process#Belief_update).

## Task 2

Solving a POMDP using the [SARSOP](https://github.com/AdaCompNUS/sarsop) solver.

The problem statements for task 1 and task 2 have been explained in detail in [Assignment_Part1.pdf](https://github.com/codelixir/pomdp/blob/main/Assignment_Part1.pdf) and [Assignment_Part2.pdf](https://github.com/codelixir/pomdp/blob/main/Assignment_Part2.pdf) respectively.