Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Safe and fast exploration for reinforcement learning using constrained action manifolds

Safe and fast exploration for reinforcement learning using constrained action manifolds

US Patent 11823039 · Granted Nov 21, 2023

Estimated economic value: $7,457,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Image anomaly detection by enhancing patched features2025
Transfer anomaly detection using online deep sets2025
Learning unpaired multimodal feature matching for semi-supervised learning2025
Sound anomaly detection with mixed augmented datasets2024
Sequential learning of constraints for hierarchical reinforcement learning2023
Sequential learning of constraints for hierarchical reinforcement learning2023
Sequential learning of constraints for hierarchical reinforcement learning2023
Anomaly detection by ranking from algorithm2023
Anomaly detection by ranking from algorithm2023
Sim-to-real learning of 2D multiple sound source localization2023
Text-based response environment action selection2023
Imitation learning by action shaping with antagonist reinforcement learning2022