We report on the use of reinforcement learning with Cobot, a software agent residing in the wellknown online community LambdaMOO. Our initial work on Cobot (Isbell et al.2000) pro...
Charles Lee Isbell Jr., Christian R. Shelton, Mich...
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
We describe an algorithm for learning in the presence of multiple criteria. Our technique generalizes previous approaches in that it can learn optimal policies for all linear pref...
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...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...