Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Action selection for reinforcement learning using a manager neural network that generates goal vectors defining agent objectives

Action selection for reinforcement learning using a manager neural network that generates goal vectors defining agent objectives

US Patent 11537887 · Granted Dec 27, 2022

Estimated economic value: $61,722,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Progressive neural networks2025
Generating predictions characterizing images using glimpses extracted from the i2025
Distributed training using actor-critic reinforcement learning with off-policy c2025
Energy-based associative memory neural networks2025
Reinforcement learning for active sequence processing2024
Modulating agent behavior to optimize learning progress2024
Reinforcement learning using baseline and policy neural networks2024
Parallel video processing systems2024
Generating discrete latent representations of input data items2024
Image processing of an environment to select an action to be performed by an age2024
Using hierarchical representations for neural network architecture searching2024
Distributed training using actor-critic reinforcement learning with off-policy c2024