Hiteshi Sharma

Hiteshi Sharma

Auto-generated profile, based on publicly available information

Hiteshi Sharma

University of Southern California,EE Department

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
WHWilliam B. Haskell
William B. Haskell
RJRahul Jain
Rahul Jain
HSHiteshi Sharma
Hiteshi Sharma
PYPengqian Yu
Pengqian Yu
We propose universal randomized function approximation-based empirical value learning (EVL) algorithms for Markov decision processes. The “empirical” nature comes from each iteration being done empirically from samples available from simulations of the next state. This makes the Bellman operator a random operator. A parametric and a nonparametric method for function approximation using a parametric function space and a reproducing kernel Hilbert space respectively are then combined with EVL. Both function spaces have the universal function approximation property. Basis functions are picked randomly. Convergence analysis is performed using a random operator framework with techniques from the theory of stochastic dominance. Finite time sample complexity bounds are derived for both universal approximate dynamic programming algorithms. Numerical experiments support the versatility and computational tractability of this approach.

1 December 2019
Verified
Conference Paper
Closed access
HSHiteshi Sharma
Hiteshi Sharma
RJRahul Jain
Rahul Jain
WHWilliam Haskell
William Haskell
In this paper, we present Randomized Empirical Value Learning (RAEVL) algorithm for MDPs with continuous state and action spaces. This algorithm combines the ideas of random search over action space with randomized function approximation method to generalize the value functions over state space . Our theoretical analysis is done under a random operator framework combined with stochastic dominance argument. This provides finite-time analysis of the proposed algorithm as well as give the sample complexity.