For a contractive iterated function system (IFS), it is known that there natural hyperbolic graph structure (augmented tree) on the symbolic space of IFS reflects relationship among neighboring cells, and its boundary with Gromov metric Hölder equivalent to attractor K [14], [26], [28]. This setup was taken up study probabilistic potential theory [21], [20], bi-Lipschitz equivalence [29]. In th...

Policy iteration algorithms for partially observable Markov decision processes (POMDP) offer the benefits of quick convergence and the ability to operate directly on the solution, which usually takes the form of a finite state controller. However, the controller tends to grow quickly in size across iterations due to which its evaluation and improvement become costly. Bounded policy iteration pr...

We present a method for efficient learning of control policies for multiple related robotic motor skills. Our approach consists of two stages: joint training and specialization training. During joint training, a single neural network policy is trained to perform multiple tasks. This forces the policy to learn a common representation of the different tasks. Then, during the specialization traini...

Loop scheduling is an important issue in the development of high performance multiprocessors. As modern multiprocessors have high and non-uniform memory access (NUMA) costs, the communication costs dominate the execution of parallel programs. Previous anity algorithms perform better than dynamic algorithms under non-clustered NUMA multiprocessors, but they su€er heavy overheads when migrating ...