Grandmaster level in StarCraft II using multi-agent reinforcement learning

Oriol Vinyals, I. Babuschkin, Wojciech Marian Czarnecki, +38

Nature

Artificial IntelligenceGame AiMulti-agent Reinforcement LearningEngineeringGame Theory +4

Prioritized Experience Replay

Tom Schaul, John Quan, Ioannis Antonoglou, +1

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningSequential LearningEducation +15

Dueling Network Architectures for Deep Reinforcement Learning

Ziyu Wang, Tom Schaul, Matteo Hessel, +3

arXiv (Cornell University)

Artificial IntelligenceDeep RepresentationsConventional ArchitecturesModel-free LearningEngineering +12

Rainbow: Combining Improvements in Deep Reinforcement Learning

Matteo Hessel, Joseph Modayil, Hado van Hasselt, +7

Proceedings of the AAAI Conference on Artificial Intelligence

Artificial IntelligenceCombining ImprovementsAtari 2600EngineeringMachine Learning +13

Deep Q-learning From Demonstrations

Todd Hester, Matej Vecerík, Olivier Pietquin, +11

Proceedings of the AAAI Conference on Artificial Intelligence

Artificial IntelligenceEngineeringMachine LearningEducationReinforcement Learning (Educational Psychology) +16

StarCraft II: A New Challenge for Reinforcement Learning

Oriol Vinyals, Timo Ewalds, Sergey Bartunov, +22

arXiv (Cornell University)

Artificial IntelligenceGame AiEngineeringMachine LearningGame Theory +16

Unifying count-based exploration and intrinsic motivation

Marc G. Bellemare, Sriram Srinivasan, Georg Ostrovski, +3

Neural Information Processing Systems

Artificial IntelligenceEngineeringMachine LearningBehavioral Decision MakingGame Theory +19

Universal Value Function Approximators

Tom Schaul, Daniel Horgan, Karol Gregor, +1

Numerical AnalysisArtificial IntelligenceEngineeringMachine LearningSeparate Embedding Vectors +15

Rainbow: Combining Improvements in Deep Reinforcement Learning

Matteo Hessel, Joseph Modayil, Hado van Hasselt, +7

arXiv (Cornell University)

Artificial IntelligenceCombining ImprovementsAtari 2600EngineeringMachine Learning +13

Learning to learn by gradient descent by gradient descent

Marcin Andrychowicz, Misha Denil, Sergio Luis Suárez Gómez, +5

arXiv (Cornell University)

Artificial IntelligenceGradient DescentMachine VisionMachine LearningEngineering +12