Non-trivial two-armed partial-monitoring games are bandits
نویسندگان
چکیده
We consider online learning in partial-monitoring games against an oblivious adversary. We show that when the number of actions available to the learner is two and the game is nontrivial then it is reducible to a bandit-like game and thus the minimax regret is Θ( √ T ).
منابع مشابه
Playing in stochastic environment: from multi-armed bandits to two-player games
Given a zero-sum infinite game we examine the question if players have optimal memoryless deterministic strategies. It turns out that under some general conditions the problem for twoplayer games can be reduced to the same problem for one-player games which in turn can be reduced to a simpler related problem for multi-armed bandits. Digital Object Identifier 10.4230/LIPIcs.FSTTCS.2010.65
متن کاملUtility-based Dueling Bandits as a Partial Monitoring Game
Partial monitoring is a generic framework for sequential decision-making with incomplete feedback. It encompasses a wide class of problems such as dueling bandits, learning with expect advice, dynamic pricing, dark pools, and label efficient prediction. We study the utility-based dueling bandit problem as an instance of partial monitoring problem and prove that it fits the time-regret partial m...
متن کاملCombinatorial Partial Monitoring Game with Linear Feedback and Its Applications
In online learning, a player chooses actions to play and receives reward and feedback from the environment with the goal of maximizing her reward over time. In this paper, we propose the model of combinatorial partial monitoring games with linear feedback, a model which simultaneously addresses limited feedback, infinite outcome space of the environment and exponentially large action space of t...
متن کاملGeneric Exploration and K-armed Voting Bandits
We study a stochastic online learning scheme with partial feedback where the utility of decisions is only observable through an estimation of the environment parameters. We propose a generic pure-exploration algorithm, able to cope with various utility functions from multi-armed bandits settings to dueling bandits. The primary application of this setting is to offer a natural generalization of ...
متن کاملLatent Bandits
We consider a multi-armed bandit problem where the reward distributions are indexed by two sets –one for arms, one for type– and can be partitioned into a small number of clusters according to the type. First, we consider the setting where all reward distributions are known and all types have the same underlying cluster, the type’s identity is, however, unknown. Second, we study the case where ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1108.4961 شماره
صفحات -
تاریخ انتشار 2011