There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most...
Many algorithms such as Q-learning successfully address reinforcement learning in single-agent multi-time-step problems. In addition there are methods that address reinforcement l...
Reinforcement Programming (RP) is a new technique for automatically generating a computer program using reinforcement learning methods. This paper describes how RP learned to gene...
Spencer K. White, Tony R. Martinez, George L. Rudo...
This paper presents a reinforcement learning algorithm used to allocate tasks to agents in an uncertain real-time environment. In such environment, tasks have to be analyzed and a...