5 citations · 14 across the 10 of their papers we have counts for
9 papers · 1 filter
Sufficient Exploration for Convex Q-learning
Fan Lu, Prashant Mehta, Sean Meyn +1
In recent years there has been a collective research effort to find new formulations of reinforcement learning that are simultaneously more efficient and more amenable to analysis.…
A Dynamic Programming Formulation for the Nonlinear Filter
Jin Won Kim, Prashant G. Mehta
This paper build on our recent work where we presented a dual stochastic optimal control formulation of the nonlinear filtering problem [1]. The constraint for the dual problem is…
Feedback Particle Filter for Collective Inference
Jin Won Kim, Amirhossein Taghvaei, Yongxin Chen +1
The purpose of this paper is to describe the feedback particle filter algorithm for problems where there are a large number () of non-interacting agents (targets) with a large n…
Convex Q-Learning, Part 1: Deterministic Optimal Control
Prashant G. Mehta, Sean P. Meyn
It is well known that the extension of Watkins' algorithm to general function approximation settings is challenging: does the projected Bellman equation have a solution? If so, is…
Optimal Rate of Convergence for Quasi-Stochastic Approximation
Andrey Bernstein, Yue Chen, Marcello Colombino +3
The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic frameworks for reinforcement learning (RL), and often an efficient approach to solving (or…
What is the Lagrangian for Nonlinear Filtering?
Jin W. Kim, Prashant G. Mehta, Sean P. Meyn
Duality between estimation and optimal control is a problem of rich historical significance. The first duality principle appears in the seminal paper of Kalman-Bucy, where the prob…