— We address a lifetime maximization problem for a single-hop wireless sensor network where multiple sensors encode and communicate their measurements of a Gaussian random source...
A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...
Most approaches for model checking software are based on ration of abstract models from source code, which may greatly reduce the search space, but may also introduce errors that a...
Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...