The execution order of a block of computer instructions can make a difference in its running time by a factor of two or more. In order to achieve the best possible speed, compiler...
Consider the task of exploring the Web in order to find pages of a particular kind or on a particular topic. This task arises in the construction of search engines and Web knowled...
This paper presents a self-organizing cognitive architecture, known as TD-FALCON, that learns to function through its interaction with the environment. TD-FALCON learns the value ...
We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...