Mohit Prashant

Mohit Prashant

I am an AI researcher with a focus in machine learning safety and risk. My PhD work is in deriving probabilistic guarantees for RL systems and agents using learning theory (PAC framework).

Efficiently Scaling Model-Free Reinforcement Learning with Local Approximation

Date:

Presented a guest lecture at UPenn, SEAS on efficient scaling of RL systems such that the sample-complexity of learning is a linear function of state-space size using localized MDP approximations, improving on SOTA log-linear scaling bounds. The full paper is available here.