Reinforcement Learning
"Reinforcement learning is learning what to do – how to map situations to actions – so as to maximize a numerical reward signal. The learner is not told which actions to take, as in most forms of machine learning, but instead must discover which actions yield the most reward by trying them."
– Sutton, Richard S. and Andrew G. Barto. Reinforcement Learning: An Introduction. (1.1). MIT Press, Cambridge, MA, 1998.
ProvablyFeedback-EfficientReinforcementLearning viaActiveRewardLearning
Neural Information Processing Systems
Here H is the horizon oftheRL environment, anddimR specifies thecomplexity ofthefunction class representing the reward function.
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.49)
Country:
- North America > United States > California > Los Angeles County > Long Beach (0.14)
- Europe > Switzerland > Zรผrich > Zรผrich (0.14)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.04)
- (16 more...)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.46)
Country:
- North America > United States > California > Los Angeles County > Long Beach (0.14)
- Europe > Switzerland > Zรผrich > Zรผrich (0.14)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.05)
- (16 more...)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.94)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.46)
SecurityAnalysisofSafeandSeldonian ReinforcementLearningAlgorithms
Neural Information Processing Systems
This component makes current Seldonian algorithms safe: the safety test checks whether necessary safety constraints are satisfiedwithhighprobability.
Country:
- North America > United States (0.28)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
Industry:
- Health & Medicine > Therapeutic Area > Endocrinology > Diabetes (0.96)
- Government (0.68)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.47)
Country:
- South America > Chile > Santiago Metropolitan Region > Santiago Province > Santiago (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Europe > France > Auvergne-Rhรดne-Alpes > Isรจre > Grenoble (0.04)
- Asia > Middle East > Jordan (0.04)
Industry:
- Information Technology (0.46)
- Energy (0.46)
Technology:
- Information Technology > Game Theory (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.70)
- Information Technology > Data Science (0.68)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (0.47)
Country:
- Europe > Russia (0.04)
- Asia > Russia (0.04)
- North America > United States > Virginia (0.04)
- (2 more...)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
Country:
- North America > United States > Pennsylvania (0.04)
- Asia > Middle East > Republic of Tรผrkiye > Aksaray Province > Aksaray (0.04)
Technology:
- Information Technology > Artificial Intelligence > Robots (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
SupplementaryMaterialof RefactoringPolicyforCompositionalGeneralizability usingSelf-SupervisedObjectProposals
Neural Information Processing Systems
Concretely,theimage isdivided intoH W cells, and each cell represents a potential foreground object.
Country: North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.46)
Country:
- North America > United States > California > San Diego County > San Diego (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Asia > China > Shanghai > Shanghai (0.04)
Industry:
- Education (0.48)
- Leisure & Entertainment > Games (0.47)
Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.70)
- Information Technology > Artificial Intelligence > Vision (0.68)
- Information Technology > Sensing and Signal Processing > Image Processing (0.68)
- (2 more...)
Country:
- North America > Canada > British Columbia (0.05)
- North America > Canada > Quebec > Montreal (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.86)