Pursuit-Evasion Without Regret, with an Application to Trading

نویسندگان

  • Lili Dworkin
  • Michael Kearns
  • Yuriy Nevmyvaka
چکیده

We propose a state-based variant of the classical online learning problem of tracking the best expert. In our setting, the actions of the algorithm and experts correspond to local moves through a continuous and bounded state space. At each step, Nature chooses payoffs as a function of each player’s current position and action. Our model therefore integrates the problem of prediction with expert advice with the stateful formalisms of reinforcement learning. Traditional no-regret learning approaches no longer apply, but we propose a simple algorithm that provably achieves no-regret when the state space is any convex Euclidean region. Our algorithm combines techniques from online learning with results from the literature on pursuitevasion games. We describe a natural quantitative trading application in which the convex region captures inventory risk constraints, and local moves limit market impact. Using historical market data, we show experimentally that our algorithm has a strong advantage over classic noregret approaches.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Synthesizing Strategies for Epistemic Goals by Epistemic Model Checking: An Application to Pursuit Evasion Games

The paper identifies a special case in which the complex problem of synthesis from specifications in temporal-epistemic logic can be reduced to the simpler problem of model checking such specifications. An application is given of strategy synthesis in pursuit-evasion games, where one or more pursuers with incomplete information aim to discover the existence of an evader. Experimental results ar...

متن کامل

Intelligent pursuit & evasion in an unknown environment

This paper introduces a novel and flexible simulation platform for studying pursuit and evasion in unknown 2-D environments of arbitrary obstacles, in an effort to expand the practical application of pursuit-evasion research. The platform provides realistic simulation of the sensing capability of each robotic agent (either a pursuer or an evader). Each agent uses real-time local sensing to coll...

متن کامل

Vision-based Detection of Autonomous Vehicles for Pursuit-evasion Games

We present a vision-based algorithm for the detection of multiple autonomous vehicles for a pursuit-evasion game scenario. Our algorithm computes estimates of the pose of multiple moving evaders from visual information collected by multiple moving pursuers, without previous knowledge of the segmentation of the image measurements or the number of moving evaders. We evaluate our algorithm in purs...

متن کامل

Model Checking Knowledge in Pursuit Evasion Games

In a pursuit-evasion game, one or more pursuers aim to discover the existence of, and then capture, an evader. The paper studies pursuit-evasion games in which players may have incomplete information concerning the game state. A methodology is presented for the application of a model checker for the logic of knowledge and time to verify epistemic properties in such games. Experimental results a...

متن کامل

Visibility-Based Pursuit-Evasion with Limited Field of View

We study the visibility-based pursuit-evasion problem, in which one or more searchers must move through a given environment so as to guarantee detection of any and all evaders, which can move arbitrarily fast. Our goal is to develop techniques for coordinating teams of robots to execute this task in application domains such as clearing a building, for reasons of security or safety. To this end,...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014