Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > sci.physics > #521756

Re: Single photon decision-maker solves multi-armed bandit problem

Show all headers | View raw

   Review for the jimp | Multi-armed bandit
> https://en.wikipedia.org/wiki/Multi-armed_bandit

> In probability theory, the multi-armed bandit problem (sometimes
> called the K-[1] or N-armed bandit problem[2]) is a problem in which
> a gambler at a row of slot machines (sometimes known as "one-armed
> bandits") has to decide which machines to play, how many times to
> play each machine and in which order to play them.[3] When played,
> each machine provides a random reward from a distribution specific to
> that machine. The objective of the gambler is to maximize the sum of
> rewards earned through a sequence of lever pulls.[4][5]
>
> Robbins in 1952, realizing the importance of the problem, constructed
> convergent population selection strategies in "some aspects of the
> sequential design of experiments".[6]
>
> A theorem, the Gittins index published first by John C. Gittins gives
> an optimal policy in the Markov setting for maximizing the expected
> discounted reward.[7]
>
> In practice, multi-armed bandits have been used to model the problem
> of managing research projects in a large organization, like a science
> foundation or a pharmaceutical company. Given a fixed budget, the
> problem is to allocate resources among the competing projects, whose
> properties are only partially known at the time of allocation, but
> which may become better understood as time passes.[4][5]
>
> In early versions of the multi-armed bandit problem, the gambler has
> no initial knowledge about the machines. The crucial tradeoff the
> gambler faces at each trial is between "exploitation" of the machine
> that has the highest expected payoff and "exploration" to get more
> information about the expected payoffs of the other machines. The
> trade-off between exploration and exploitation is also faced in
> reinforcement learning.


-- 

sci.physics is an unmoderated newsgroup dedicated
to the discussion of physics, news from the physics
community, and physics-related social issues.

Back to sci.physics | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

Single photon decision-maker solves multi-armed bandit problem Sam Wormley <swormley1@gmail.com> - 2015-09-17 16:25 -0500
  Re: Single photon decision-maker solves multi-armed bandit problem jimp@specsol.spam.sux.com - 2015-09-17 21:46 +0000
    Re: Single photon decision-maker solves multi-armed bandit problem Sam Wormley <swormley1@gmail.com> - 2015-09-17 21:07 -0500
      Re: Single photon decision-maker solves multi-armed bandit problem jimp@specsol.spam.sux.com - 2015-09-18 03:14 +0000
        Re: The ass hat spams some more jimp@specsol.spam.sux.com - 2015-09-18 17:46 +0000
      Re: Single photon decision-maker solves multi-armed bandit problem "reber g=emc^2" <herbertglazier0@gmail.com> - 2015-09-18 11:43 -0700
        Re: Single photon decision-maker solves multi-armed bandit problem benj <nobody@gmail.com> - 2015-09-18 14:48 -0400
        Re: Single photon decision-maker solves multi-armed bandit problem Double-A <double-a3@hush.com> - 2015-09-18 16:29 -0700
          Re: Single photon decision-maker solves multi-armed bandit problem "reber g=emc^2" <herbertglazier0@gmail.com> - 2015-09-20 09:47 -0700
  Re: Single photon decision-maker solves multi-armed bandit problem "Y.Porat" <y.y.porat@gmail.com> - 2015-09-19 01:55 -0700
    Re: Single photon decision-maker solves multi-armed bandit problem "Oliver Jacob Bacon" <invalid@example.com> - 2015-09-19 07:58 -0700
  Re: Single photon decision-maker solves multi-armed bandit problem "Y.Porat" <y.y.porat@gmail.com> - 2015-09-19 01:57 -0700
    Re: Single photon decision-maker solves multi-armed bandit problem "Oscar Jazz Bottom" <invalid@example.com> - 2015-09-19 07:57 -0700
      Re: Single photon decision-maker solves multi-armed bandit problem "Y.Porat" <y.y.porat@gmail.com> - 2015-09-20 01:21 -0700

csiph-web