Pinned Loading

1. Reinforcement-Learning-Snake-Game-agent Reinforcement-Learning-Snake-Game-agent Public

   Used Deep Reinforcement Learning to make an agent that masters the Snake Game... It uses the Q learning algorithm to be specific and a neural network to generalize the reward for each state. It's f…

   Python 1

2. Spot-micro-rugged-terrain-rl-sim Spot-micro-rugged-terrain-rl-sim Public

   Reinforcement Learning-based rugged terrain locomotion for the SpotMicro quadruped using Augmented Random Search (ARS) in PyBullet. Fine-tunes flat-ground walking policies on randomized heightfield…

   Python 1

3. micrograd micrograd Public

   I built an autograd from scratch and my own fully functioning neural network from scratch.

   Jupyter Notebook

4. Paint-Spraying-on-a-Wall-Mesh-simulation Paint-Spraying-on-a-Wall-Mesh-simulation Public

   This project demonstrates how particle simulation, procedural texture generation, and OpenUSD visualization can be combined to model an automated spray painting process. The system captures the ess…

   Python 1 1

5. Research-Paper-Emotionally-Intelligent-Robot-framework-for-Workplace-Environments Research-Paper-Emotionally-Intelligent-Robot-framework-for-Workplace-Environments Public

   Worked with Dr. Armaan Garg and designed and developed an emotionally and socially aware robotic system aimed at improving human-robot interaction in academic environments.

6. osrf/rocker osrf/rocker Public

   A tool to run docker containers with overlays and convenient options for things like GUIs etc.

   Python 734 100