. "Reinforcement learning"@en . . "6" . "Deep reinforcement learning is a field of Artificial Intelligence that has attracted much attention since impressive achievements in Robotics, Atari, and most recently Go, where human world champions were defeated by computer players. These results build upon a combination of the rich history of reinforcement learning research and deep learning.\r\nThis course teaches the field of deep reinforcement learning: How does it work, why does it work, and what are the reinforcement learning methods on which Robotics and AlphaGo’s success are based? By the end of the course you should have acquired a good understanding of the field of deep reinforcement learning.\r\n\r\nThe defining characteristic of reinforcement learning is that agents learn through interaction with an environment, not unlike humans learn by doing. Instead of telling a learner which action to take, the agent analyzes which action to take so as to maximize a reward signal. Reinforcement learning is a powerful technique for solving sequential decision problems.\r\n\r\nThe defining characteristic of deep learning is that the model generalizes, it build a hierarchy of abstract features from its inputs.\r\n\r\nProminent reinforcement learning problems occur, amongst others, in games and robotics. In this course you will learn the necessary theory to apply reinforcement learning to realistic problems from the field of computer game playing.\n\nThe following topics and algorithms are planned to be discussed:\r\n\r\nTabular Value-based Reinforcement Learning, such as Q-learning\r\nDeep Value-based Reinforcement Learning, such as DQN\r\nPolicy-based Reinforcement Learning, such as PPO\r\nModel-based Reinforcement Learning\r\nTwo-Agent Self-Play (AlphaGo)\r\nMulti-Agent Reinforcement Learning (Poker, StarCraft)\r\nHierarchical Reinforcement Learning\r\nMeta-Learning, such as MAML\r\nBrief Summary of Deep Supervised Learning\r\n\r\nIn addition the role of reinforcement learning in artificial intelligence and the relation with psychology will be discussed (human learning).\r\nThis a hands-on course, in which you will be challenged to build working game playing programs with different reinforcement learning methods. This is a challenging course in which proficiency in Python and deep learning libraries (such as Keras and PyTorch) is important.\r\nAll assignments should be made in Python.\n\nOutcome:\nAfter completing the reinforcement learning course, the students should be able to:\r\n\r\nUnderstand the key features and components of deep reinforcement learning;\r\nKnowledge of theoretical foundations on basic and advanced deep reinforcement learning techniques;\r\nUnderstand the scientific state-of-the-art in the field of deep reinforcement learning." . . "Presential"@en . "TRUE" . . "Others"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "Master of Astronomy and Data Science"@en . . "https://www.universiteitleiden.nl/en/education/study-programmes/master/astronomy/astronomy-and-data-science" . "120"^^ . "Presential"@en . "In the master’s specialisation Astronomy and Data Science you focus on development and application of new data-mining technologies, fully embracing modern astronomy as a data rich science. You combine the research curriculum in Astronomy with in-depth training in Computer Science.\n\nThe Astronomy and Data Science master’s programme is built on world-class computational astrophysics research as well as hightech industry expertise. It covers a wide range of research areas studying complex astronomical phenomena, including radiative transfer, computation of dynamical internal galaxy structures and hydrodynamical modeling of galaxy formation and evolution of the intergalactic medium.\n\nThis two-year Astronomy and Data Sicence programme uniquely combines advanced Astronomy courses of the Leiden Observatory and relevant courses from the Computer Science master’s programme of the Leiden Institute of Advanced Computer Science including advanced data mining and neural networks. To this end, the Leiden Observatory offers sophisticated computational facilities ranging from local computer clusters to high-performance systems at national and international computing centers.\n\nOutcome:\nDuring the programme, you learn to perform academically sound research and evaluate scientific information independently and critically. Without exception, you actively participate in current research within the institute and are individually supervised by our international scientific staff. Students with a Leiden degree in Astronomy become strong communicators and collaborators and can easily operate in an international setting. You will acquire extensive astronomical research experience and highly advanced analytical and problem solving skills."@en . . . . . . "2"@en . "FALSE" . . "Master"@en . "Thesis" . "2314.00" . "Euro"@en . "19600.00" . "Mandatory" . "Most graduates holding a MSc degree in Astronomy from Leiden University find work in many different capacities, including:\n\n1. Research: universities, observatories, research institutes\n2. Industry and consultancy: ICT, R&D, telecom, high technology, aerospace\n3. Finance: banking, insurance, pension funds\n4. Public sector: governments, policy makers, high schools\n5. Science communication: journalism, popular writing, museums\n6. Typical jobs for Astronomy graduates include:\n\nScientific researcher (postdoc, research fellow, professor)\n1. R&D engineer\n2. Consultant\n3. Data scientist, statistician\n4. Policy advisor, public information officer (e.g. Ministry of Foreign Affairs)\n5. High school physics teacher\n6. Scientific editor for magazines, newspapers and other media\n7. Research at Leiden Observatory\n\nIf you want to get more deeply involved in research after graduating in Astronomy, consider pursuing a PhD at Leiden Observatory. If you have completed the Leiden master’s degree programme in Astronomy, you are directly eligible for admission to our PhD programme"@en . "no data" . "TRUE" . "Upstream"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .