Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Method for adaptive exploration to accelerate deep reinforcement learning

Method for adaptive exploration to accelerate deep reinforcement learning

US Patent 11886988 · Granted Jan 30, 2024

Estimated economic value: $13,656,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Neural network hardware accelerator data parallelism2024
Sequence partition based schedule optimization2024
Neural network accelerator writable memory2024
Neural network hardware accelerator data parallelism2023
Neural network cooperation2023
Neural network cooperation2023
Hardware and neural architecture co-search2022
Dynamic Boltzmann machine for estimating time-varying second moment2022
Autonomous trading with memory enabled neural network learning2022
Dynamic boltzmann machine for predicting general distributions of time series da2021
Preparation and execution of quantized scaling on integrated circuitry2021
Cooperative neural network deep reinforcement learning with partial input assist2021