The success of stochastic algorithms is often due to their ability to effectively amplify the performance of search heuristics. This is certainly the case with stochastic sampling ...
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...
We investigate how to automatically verify that resources such as files are not used improperly or unsafely by a program. We employ a mixture of compile-time analysis and run-time ...
Agents often have to construct plans that obey deadlines or, more generally, resource limits for real-valued resources whose consumption can only be characterized by probability d...
We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the controlling agent. If these ev...