Deep learning

Planning and Learning For Decentralized MDPs With Event Driven Rewards

Planning and Learning For Decentralized MDPs With Event Driven Rewards

Successor Features Based Multi-Agent RL for Event-Based Decentralized MDPs

Human Activity Recognition

Classifying human activity recognition amongst six categories using Support Vector Machines and Recurrent Neural Networks (RNNs) with Long Short-Term Memory cells (LSTMs).

Planning and Learning For Decentralized MDPs With Event Driven Rewards

Developed novel algorithms for improving the scalability of solving event based Decentralized (PO)MDPs.

Spam Mail Filtering

Analyzing and comparing the performance of various classification algorithms for spam filtering.

Successor Features Based Multi-Agent RL for Event-Based Decentralized MDPs

Developed state of the art Reinforcement Learning (RL) algorithms to achieve scalable and generic learning across different environments in multi-agent systems.