Artificial intelligence

Security in Multiagent Systems by Policy Randomization

Implemented algorithms to randomize single agent MDPs by maximizing a weighted entropy function and maintaining a certain threshold of reward.

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).

AI for Ultimate Tic Tac Toe

Developed an automated AI based player for Ultimate Tic Toe implemented in Python using Greedy Heuristic based Alpha Beta Pruning and optimizing the depth of the search tree.

AI for Ultimate Tic Tac Toe

Developed an automated AI based player for Ultimate Tic Toe implemented in Python using Greedy Heuristic based Alpha Beta Pruning and optimizing the depth of the search tree.

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.