Policy gradient (PG) reinforcement learning algorithms have strong (local) convergence guarantees, but their learning performance is typically limited by a large variance in the e...
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
We analyze a simple and natural on-line algorithm (dispatch policy) for a dynamic multiperiod uncapacitated routing problem, in which at the beginning of each time period a set of...
Enrico Angelelli, Martin W. P. Savelsbergh, Maria ...
Reinforcement Learning (RL) is analyzed here as a tool for control system optimization. State and action spaces are assumed to be continuous. Time is assumed to be discrete, yet th...
The presented image registration method uses a regularized gradient flow to correlate the intensities in two images. Thereby, an energy functional is successively minimized by des...