Raj Ghugare

Raj Ghugare

I am currently working as a research intern at MILA, advised by Glen Berseth. During my undergraduate, I worked on model-based RL, advised by Ben Eysenbach. I studied electronics and communications engineering from VNIT Nagpur.

My research studies reinforcement learning, aiming at building autonomous agents that make decisions. To achieve this, agents should learn to abstract their world, both temporally and spatially, by learning latent representations, skills and models of the world.

If you want to get in touch with me, please mail me at rajghugare.vnit@gmail.com.

Twitter  /  Github  /  Google Scholar

Publications

Simplyfying moded-based RL: Learning representations, latent-space models and policies with one objective.

Reports

Reproducibility study of the Value Equivalence principle for Model Based Reinforcement Learning.