Pinned Loading

1. The repository contains code for Softmax Policy Mirror Ascent (SPMA), a policy optimization algorithm that is based on mirror ascent in the space of logits using the log-sum-exp mirror map.

   Python

2. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

   Python

3. 3D Subscene Retrieval

   Python 1

4. I'm implementing the SSD algorithm for classification and localization of multiple objects.

   Jupyter Notebook

5. Implementing a keyboard to navigate a robot safely using 2D LiDAR data.

   Makefile

6. In this project I have built and app which takes user's location of interest in San Fransisco as input. In return it allows the user to visualize clusters of population around the input location.

   Python 1