Robustness of linearly solvable Markov games employing inaccurate dynamics model
Sign Up to like & getrecommendations! Published in 2017 at "Artificial Life and Robotics"
DOI: 10.1007/s10015-017-0401-2
Abstract: As a model-based reinforcement learning technique, linearly solvable Markov decision process (LMDP) gives an efficient way to find an optimal policy by making the Bellman equation linear under some assumptions. Since LMDP is regarded as… read more here.
Keywords: control policy; model; linearly solvable; solvable markov ... See more keywords