Implemented a reformed architecture that uses Proximal Policy Optimization for training the agent and uses Behavior Cloning for incorporating expert trajectories.
An effort to make an automated robot capable of mananging (picking and placing) books in the institute library.
A transformer based Language model BERT trained on NarrativeQA dataset.
A fake-news detector based on BERT Language model.
Policy gradient algorithms on Lunar lander environment
Robotic Palm control using hand-pose estimation algorithms on live video feed
Implementation of LIRL algorithms on Mountain Car Environment.
A working prototype of a low cost safety device for fishing vessels to prevent collisions.