In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
James L. Carroll, Todd S. Peterson, Kevin D. Seppi
We present a local learning rule in which Hebbian learning is conditional on an incorrect prediction of a reinforcement signal. We propose a biological interpretation of such a fr...
P. Read Montague, Peter Dayan, Steven J. Nowlan, T...
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...