arXiv (Cornell University) · 2018 · 20 citations · 12 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningRoboticsAction SelectionPolicy LearningReinforcement LearningReinforcement Learning FoundationsAction Space FormulationContinuous Space RepresentationDeep Reinforcement LearningLearning DomainsReinforcement Learning For RoboticsReinforcement Learning In GamesSwing-up ControlTree Search
A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, navigation and self-driving cars. This paper presents the necessary theoretical extensions of Alpha Zero to deal with continuous action space. We also provide some preliminary experiments on the Pendulum swing-up task, empirically showing the feasibility of our approach. Thereby, this work provides a first step towards the application of iterated search and learning in domains with a continuous action space.
12
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations
Mastering the game of Go without human knowledge
David Silver, Julian Schrittwieser, Karen Simonyan et al. · Nature · 2017 · 9.2K citations
Engineering, Educational Psychology, Cognitive Psychology +7
TensorFlow: A system for large-scale machine learning
Martı́n Abadi, Paul Barham, Jianmin Chen et al. · arXiv (Cornell University) · 2016 · 8.8K citations · Full text