Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Paivine, William"'
State-of-the-art distributed algorithms for reinforcement learning rely on multiple independent agents, which simultaneously learn in parallel environments while asynchronously updating a common, shared policy. Moreover, decentralized control archite
Externí odkaz:
http://arxiv.org/abs/1901.08537
Autor:
Salman, Hadi, Singhal, Puneet, Shankar, Tanmay, Yin, Peng, Salman, Ali, Paivine, William, Sartoretti, Guillaume, Travers, Matthew, Choset, Howie
Recent literature in the robotics community has focused on learning robot behaviors that abstract out lower-level details of robot control. To fully leverage the efficacy of such behaviors, it is necessary to select and sequence them to achieve a giv
Externí odkaz:
http://arxiv.org/abs/1803.01446