Search Machine Learning Repository: @inproceedings{icml2014c2_dworkin14,
    Publisher = {JMLR Workshop and Conference Proceedings},
    Title = {Pursuit-Evasion Without Regret, with an Application to Trading},
    Url = {http://jmlr.org/proceedings/papers/v32/dworkin14.pdf},
    Abstract = {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 pursuit-evasion games. We describe a 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 no-regret approaches.},
    Author = {Lili Dworkin and Michael Kearns and Yuriy Nevmyvaka},
    Editor = {Tony Jebara and Eric P. Xing},
    Year = {2014},
    Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
    Pages = {1521-1529}
   }