activity
20152026
most citedCumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control

56 citations · 68 across the 13 of their papers we have counts for

collaborators
Showing 2018Show all

2 papers · 1 filter

math.OC2018★ 1 cited

Random directions stochastic approximation with deterministic perturbations

Prashanth L A, Shalabh Bhatnagar, Nirav Bhavsar +2

We introduce deterministic perturbation schemes for the recently proposed random directions stochastic approximation (RDSA) [17], and propose new first-order and second-order algor…

math.NA2018

Optimal Unbiased Estimation for Expected Cumulative Cost

Zhenyu Cui, Michael C. Fu, Yijie Peng +1

We consider estimating an expected infinite-horizon cumulative discounted cost/reward contingent on an underlying stochastic process by Monte Carlo simulation. An unbiased estimato…