Most interesting agent-environment systems have large state spaces, so performance depends crucially on efficient generalization from a small amount of experience. Current algorithms rely on ...

In such cases it is suggested that the random-phase approximation is in need of generalization. Examples are the uniform translational motion of any system and the rotational motion of deformed nuclei ...

Model-Based Exploration in Continuous State Spaces. Nicholas K. Jong and Peter Stone. @InProceedings{SARA07-jong, author="Nicholas K. Jong and Peter Stone", title ...

In each iteration, the RIS parameter and the Lagrange multiplier are updated by one projected gradient step and quadratic interpolation, respectively. Its complexity only grows linearly in the number ...

but not on the generalization gradients in SCRs (see Supplementary Table 2 A). Consistent with the results of the main analyses reported in our manuscript, we did not observe any significant effects ...