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...
For many problems which would be natural for reinforcement learning, the reward signal is not a single scalar value but has multiple scalar components. Examples of such problems i...
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...