Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Continual reinforcement learning with a multi-task agent

Continual reinforcement learning with a multi-task agent

US Patent 12154029 · Granted Nov 26, 2024

Estimated economic value: $103,833,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Training machine learning models by determining update rules using neural networ2025
Environment prediction using reinforcement learning2024
Environment prediction using reinforcement learning2024
Environment prediction using reinforcement learning2024
Training neural networks using a prioritized experience memory2024
Modulating agent behavior to optimize learning progress2024
Training reinforcement learning neural networks2024
Reinforcement learning with auxiliary tasks2023
Meta-gradient updates for training return functions for reinforcement learning s2023
Training neural networks using normalized target outputs2023
Learning non-differentiable weights of neural networks using evolutionary strate2023
Training machine learning models by determining update rules using recurrent neu2023