On the numerical approximation of minimax regret rules via fictitious play
Finding numerical approximations to minimax regret treatment rules is of key interest. To do so when potential outcomes are in {0,1} we discretize the action space of nature and apply a variant of Robinson's (1951) algorithm for iterative solutions for finite two-person zero sum games. Our approach avoids the need to evaluate regret of each treatment rule in each iteration. When potential outcomes are in [0,1] we apply the so-called coarsening approach. We consider a policymaker choosing between two treatments after observing data with unequal sample sizes per treatment and the case of testing several innovations against the status quo.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Nonstationary Reinforcement Learning with Linear Function Approximation
We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Decision Theory for Treatment Choice Problems with Partial Identification
We apply classical statistical decision theory to a large class of treatment choice problems with partial identification. We show that, in a general class of problems with Gaussian likelihood, all decision rules are admi…
AllBandwidth Selection for Treatment Choice with Binary Outcomes
This study considers the treatment choice problem when outcome variables are binary. We focus on statistical treatment rules that plug in fitted values based on nonparametric kernel regression and show that optimizing tw…
regressionEmpirical Analysis of Fictitious Play for Nash Equilibrium Computation in Multiplayer Games
While fictitious play is guaranteed to converge to Nash equilibrium in certain game classes, such as two-player zero-sum games, it is not guaranteed to converge in non-zero-sum and multiplayer games. We show that fictiti…
counterfactualFast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play
This paper investigates the sublinear regret guarantees of two non-no-regret algorithms in zero-sum games: Fictitious Play, and Online Gradient Descent with constant stepsizes. In general adversarial online learning sett…