27 citations · 206 across the 63 of their papers we have counts for
8 papers · 1 filter
Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems
Ting-Jui Chang, Sapana Chaudhary, Dileep Kalathil +1
This paper addresses safe distributed online optimization over an unknown set of linear safety constraints. A network of agents aims at jointly minimizing a global, time-varying fu…
Online Robust Control of Linear Dynamical Systems with Limited Prediction
Deepan Muthirayan, Dileep Kalathil, Pramod P. Khargonekar
We study the online robust control problem for linear dynamical systems with disturbances and uncertainties in the cost functions, with limited preview of the future disturbances a…
Reinforcement Learning for Mean Field Games with Strategic Complementarities
Kiyeob Lee, Desik Rengarajan, Dileep Kalathil +1
Mean Field Games (MFG) are the class of games with a very large number of agents and the standard equilibrium concept is a Mean Field Equilibrium (MFE). Algorithms for learning MFE…
D2C 2.0: Decoupled Data-Based Approach for Learning to Control Stochastic Nonlinear Systems via Model-Free ILQR
Karthikeya S Parunandi, Aayushman Sharma, Suman Chakravorty +1
In this paper, we propose a structured linear parameterization of a feedback policy to solve the model-free stochastic optimal control problem. This parametrization is corroborated…
Empirical Q-Value Iteration
Dileep Kalathil, Vivek S. Borkar, Rahul Jain
We propose a new simple and natural algorithm for learning the optimal Q-value function of a discounted-cost Markov Decision Process (MDP) when the transition kernels are unknown.…
Empirical Dynamic Programming
William B. Haskell, Rahul Jain, Dileep Kalathil
We propose empirical dynamic programming algorithms for Markov decision processes (MDPs). In these algorithms, the exact expectation in the Bellman operator in classical value iter…
Optimal Decentralized Control with Asymmetric One-Step Delayed Information Sharing
Naumaan Nayyar, Dileep Kalathil, Rahul Jain
We consider optimal control of decentralized LQG problems for plants controlled by two players having asymmetric information sharing patterns between them. In one scenario, players…
Decentralized Learning for Multi-player Multi-armed Bandits
Dileep Kalathil, Naumaan Nayyar, Rahul Jain
We consider the problem of distributed online learning with multiple players in multi-armed bandits (MAB) models. Each player can pick among multiple arms. When a player picks an a…