Abstract. Recent work has applied the Markov Game formalism from AI to model game dynamics for ice hockey, using a large state space. Dynamic programming is used to learn action-value functions that quantify the impact of actions on goal scoring. Learning is based on a massive dataset that contains over 2.8M events in the National Hockey League. As an application of the Markov model, we use the...

In this paper, we propose a hierarchical reinforcement learning architecture for a robot with large degrees of freedom. In order to enable learning in a practical numbers of trials, we introduce a low-dimensional representation of the state of the robot for higher-level planning. The upper level learns a discrete sequence of sub-goals in a low-dimensional state space for achieving the main goal...

One popular way of exorcising the ddmon of dimensionality in dynamic programming is to consider spatial and temporal hierarchies for representing the value functions and policies. This paper develops a hierarchical method for Q-learning which is based on the familiar notion of a recursive feudal serfdom, with managers setting tasks and giving rewards and punishments to their juniors and in thei...

this paper deals with the boundary value problem involving the differential equation ell y:=-y''+qy=lambda y, subject to the eigenparameter dependent boundary conditions along with the following discontinuity conditions y(d+0)=a y(d-0), y'(d+0)=ay'(d-0)+b y(d-0). in this problem q(x), d, a , b are real, qin l^2(0,pi), din(0,pi) and lambda is a parameter independent of x. by ...