My personal portfolio.

Contrastive State Only Imitation Learning with Reducing Paradigm Gap.

Implementation of different On-Policy and Off-Policy Policy Gradient Methods

Some algorithms of Reinforcement Learning implemented by me, in accordance to "Introduction to Reinforcement Learning" by Richard Sutton and Andrew Barto.

Uploading different ML Architectures that I have made for personal use/projects.

ML Experiments for SEBI Hackathon. Looking into multimodal application in finance.

Contains Expert Trajectories for various Gym Environments used for State Only Imitation Learning

Repository containing my personal notes on ~30 State Only Imitation Learning Papers, used for a Journal Paper.

Containing codes for implementing a Physics Informed Neural Network with the PyTorch Framework based on the original work (https://github.com/maziarraissi/PINNs)

Innovative prototype automates codebase to documentation with GPT-3.5. Accurate, contextually relevant docs enhance code comprehension, boosting efficiency!

Baseline codes for a fast submission in Kaggle Competitions

Implementing GAN architectures from scratch with Torch, leading to architectures like GAIL used for Imitation Learning.

Multimodal approach to handle psychological issues, extending to psychotic disorders and suicide prevention.

Trying to code out some architectures without using any libraries except the "time" module! There is NO usage of numpy and pandas!

This dataset contains 11,070 images and their corresponding labels manually annotated by me.