search

ajay-dhangar / algo

This repository contains a collection of data structures and algorithms implemented in various programming languages. It is designed to help learners understand key concepts through hands-on examples. Contributions and improvements are welcome!
https://ajay-dhangar.github.io/algo/
MIT License
70 stars 226 forks source link

[Feature]: <Policy Gradient Methods> #1105

Closed priyashuu closed 1 week ago

priyashuu commented 1 month ago

Feature Name

Adding Policy Gradient Methods Visualizations

Feature Description

Develop policy gradient methods that directly optimize the policy by updating it toward higher expected rewards.

Motivation

Policy gradient methods are vital for solving reinforcement learning problems with continuous action spaces. Adding this feature will enhance the flexibility of the algorithms available.

Implementation Suggestions (Optional)

No response

Feature Type

New Algorithm

Does this feature require additional resources?

References (Optional)

No response

github-actions[bot] commented 1 month ago

👋 Hi @priyashuu! Thanks for opening this issue. We appreciate your contribution to the Algo project. Our team will review it soon.

priyashuu commented 2 weeks ago

please assign this issue to me @ajay-dhangar