Reinforcement learning (RL) can be impractical for many high dimensional problems because of the computational cost of doing stochastic search in large state spaces. We propose a ...
Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinfor...
Emma Brunskill, Bethany R. Leffler, Lihong Li, Mic...
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...
In this paper, we propose a dynamic allocation method of basis functions, an Allocation/Elimination Gaussian Softmax Basis Function Network (AE-GSBFN), that is used in reinforcemen...
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...