Research

I am broadly interested in Machine Learning and AI. My goal is to develop robust autonomous artificial agents with cognitive abilities to interact, coordinate, and negotiate. I am particularly interested in the following domains:

• Developing efficient algorithms for sequential decision making in mixed cooperative-competitive multi-agent environments that learn with teammates’ and opponents’ awareness.

• Conjunction of machine learning and robotics (Robot learning). Particularly using deep reinforcement learning and model-based optimization for robotics.

• Developing algorithms for adversarial learning to improve the Conditional Variance at Risk (CVaR) and achieve Sim2Real transfer with minimal degradation of performance.

• Unsupervised reinforcement learning and meta-learning.