A Two-Armed Bandit Theory of Market
نویسندگان
چکیده
Economics lacks a good theory of how stores should set their prices when they do not know the demand functions of their customers. Traditional theory either assumes that firms know their demand curves, or that they can, if necessary, find them out easily and costlessly from market experience. The market will inform the perfectly competitive firm of its demand function with ruthless efficiency. A firm which charges more than the market price will, as a matter of definition, lose all its customers. If it charges less than the market price, it will have all the customers it can handle. It is not difficult to explain how a perfectly competitive firm discovers what the market price is and all it needs to know of its deman function. Conventional theories of monopoly and imperfect competition attribute to firms’ complete knowledge of all relevant parameters of their demand relationships. Recently developed theories of firm behavior under uncertainty (for example, Baron [2] or Leland [IO]) are not exceptions. The firm is typically supposed to face a stochastic demand function of the genera% form f) = D(#, 0), where 19 is a random variable and X3(., .) a known fnnction. The firm is assumed to maximize expected profits (or the expected utility of profits). The theory does not explain how the firm comes to know D(., *) nor is it concerned with explaining how the Grm might come to know its demand function more accurately and thus reduce the uncertainty it faces.l
منابع مشابه
UDC 519.244.3 An Asymptotic Minimax Theorem for Gaussian Two-Armed Bandit
The asymptotic minimax theorem for Bernoulli two-armed bandit problem states that minimax risk has the order N as N → ∞, where N is the control horizon, and provides the estimates of the factor. For Gaussian twoarmed bandit with unit variances of one-step incomes and close expectations, we improve the asymptotic minimax theorem as follows: the minimax risk is approximately equal to 0.637N as N ...
متن کاملCognitive Capacity and Choice under Uncertainty: Human Experiments of Two-armed Bandit Problems
The two-armed bandit problem, or more generally, the multi-armed bandit problem, has been identified as the underlying problem of many practical circumstances which involves making a series of choices among uncertain alternatives. Problems like job searching, customer switching, and even the adoption of fundamental or technical trading strategies of traders in financial markets can be formulate...
متن کاملGap-free Bounds for Stochastic Multi-Armed Bandit
We consider the stochastic multi-armed bandit problem with unknown horizon. We present a randomized decision strategy which is based on updating a probability distribution through a stochastic mirror descent type algorithm. We consider separately two assumptions: nonnegative losses or arbitrary losses with an exponential moment condition. We prove optimal (up to logarithmic factors) gap-free bo...
متن کاملRisk-aware multi-armed bandit problem with application to portfolio selection
Sequential portfolio selection has attracted increasing interest in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed bandit problem addresses the primary difficulty in sequential decision-making under uncertainty, namely the exploration versus exploitation dilemma, and therefore...
متن کامل