Although several researchers have integrated methods for reinforcement learning (RL) with case-based reasoning (CBR) to model continuous action spaces, existing integrations typic...
In neuroevolution, a genetic algorithm is used to evolve a neural network to perform a particular task. The standard approach is to evolve a population over a number of generation...
Reinforcement Learning is commonly used for learning tasks in robotics, however, traditional algorithms can take very long training times. Reward shaping has been recently used to ...
Ana C. Tenorio-Gonzalez, Eduardo F. Morales, Luis ...
We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...
We call data weakly labeled if it has no exact label but rather a numerical indication of correctness of the label "guessed" by the learning algorithm - a situation comm...