Reinforcement Learning
Continuous Control of Lunar Lander Using Deep Reinforcement Learning (TD3)
I built a reinforcement learning agent from scratch in PyTorch that learns to fly and land a rocket in a physics simulator.
June 24, 2026
I built a reinforcement learning agent from scratch in PyTorch that learns to fly and land a rocket in a physics simulator.
A comparative study on improving Image Classification performance on CIFAR-10. This project implements ResNet-32 and Custom Vision Transformers (ViT) from scratch in PyTorch, utilizing Stable Diffusion (DiffuseMix) to generate synthetic training data and boost model accuracy by up to 8%.
An advanced pop music generation algorithm built with LSTM neural networks. A collaborative project focusing on improvements to baseline models and exploring parameter optimization for creative music synthesis.