Online learning via Bayes' theorem allows new data to be continuously
in...
Most modern reinforcement learning algorithms optimize a cumulative
sing...
We study the estimation of policy gradients for continuous-time systems ...
This work studies the problem of sequential control in an unknown, nonli...
This work addresses the problem of robot interaction in complex environm...
We introduce Lyceum, a high-performance computational ecosystem for robo...
We propose a plan online and learn offline (POLO) framework for the sett...
Reinforcement learning has emerged as a promising methodology for traini...