Distributional Reinforcement Learning

• Hoofdauteur: Bellemare, Marc G. (auth)
• Andere auteurs: Dabney, Will (auth), Rowland, Mark (auth)
• Formaat: Elektronisch Hoofdstuk
• Taal: Engels
• Gepubliceerd in: Cambridge The MIT Press 2023
• Reeks: Adaptive Computation and Machine Learning series
• Onderwerpen: Probability & statistics; Machine learning; Computer Science/Machine Learning & Neural Networks
• Online toegang: DOAB: download the publication; DOAB: description of the publication

The first comprehensive guide to distributional reinforcement learning, providing a new mathematical formalism for thinking about decisions from a probabilistic perspective.Distributional reinforcement learning is a new mathematical formalism for thinking about decisions. Going beyond the common app...