Amanote Research
Register
Sign In
Reducing Sample Complexity in Reinforcement Learning by Transferring Transition and Reward Probabilities
doi 10.5220/0004915606320638
Full Text
Open PDF
Abstract
Available in
full text
Date
January 1, 2014
Authors
Unknown
Publisher
SCITEPRESS - Science and and Technology Publications
Related search
Transferring Models in Hybrid Reinforcement Learning Agents
IFIP Advances in Information and Communication Technology
Computer Networks
Information Systems
Management
Communications
Transferring Task Models in Reinforcement Learning Agents
Neurocomputing
Computer Science Applications
Artificial Intelligence
Cognitive Neuroscience
Transferring Evolved Reservoir Features in Reinforcement Learning Tasks
Lecture Notes in Computer Science
Computer Science
Theoretical Computer Science
Active Learning for Reward Estimation in Inverse Reinforcement Learning
Lecture Notes in Computer Science
Computer Science
Theoretical Computer Science
Reinforcement Learning by Reward-Weighted Regression for Operational Space Control
End-To-End Robotic Reinforcement Learning Without Reward Engineering
Effects of Shaping a Reward on Multiagent Reinforcement Learning
Reinforcement Learning With Low-Complexity Liquid State Machines
Frontiers in Neuroscience
Neuroscience
Implicit Learning of First-, Second-, and Third-Order Transition Probabilities.
Journal of Experimental Psychology: Learning Memory and Cognition
Linguistics
Language
Experimental
Cognitive Psychology
