David Silver
39Patents
11h-index
53Co-inventors
78Inventor score
Filing activity: Apr 13, 1981 → Dec 4, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US5802160A | Multi-ring telephone method and system | Electricity | 209 | Expired |
| US5146491A | Telephone billing method | Electricity | 209 | Expired |
| US7493403B2 | Domain name ownership validation | Electricity | 120 | Active |
| US5045327A | Digital recording and playback module system | Physics | 79 | Expired |
| US5387943A | Semiautomatic lip sync recovery system | Electricity | 64 | Expired |
| US7761583B2 | Domain name ownership validation | Electricity | 55 | Active |
| US5276839A | System for programming EEPROM with data loaded in ROM by sending switch signal to isolate EEPROM from host system | Physics | 48 | Expired |
| US10628733B2 | Selecting reinforcement learning actions using goals and observations | Physics | 14 | Active |
| US4343409A | Large high temperature plastic vacuum reservoir | Mechanical Engineering; Lighting; Heating | 13 | Expired |
| US8909590B2 | Online asynchronous reinforcement learning from concurrent customer histories | Physics | 12 | Active |
| US10445641B2 | Distributed training of reinforcement learning systems | Physics | 11 | Active |
| US8924318B2 | Online asynchronous reinforcement learning from concurrent customer histories | Physics | 9 | Active |
| US8914314B2 | Online temporal difference learning from incomplete customer interaction histories | Physics | 9 | Active |
| US10282662B2 | Training neural networks using a prioritized experience memory | Emerging Cross-Sectional Technologies | 8 | Active |
| US9367820B2 | Online temporal difference learning from incomplete customer interaction histories | Physics | 6 | Active |
| US10346741B2 | Asynchronous deep reinforcement learning | Physics | 5 | Active |
| US11449750B2 | Training action selection neural networks using look-ahead search | Physics | 4 | Active |
| US11627165B2 | Multi-agent reinforcement learning with matchmaking policies | Electricity | 4 | Active |
| US10650310B2 | Training neural networks using a prioritized experience memory | Emerging Cross-Sectional Technologies | 3 | Active |
| US10867242B2 | Selecting actions to be performed by a reinforcement learning agent using tree search | Physics | 3 | Active |
| US10733501B2 | Environment prediction using reinforcement learning | Physics | 3 | Active |
| US10936946B2 | Asynchronous deep reinforcement learning | Physics | 2 | Active |
| US10956820B2 | Reinforcement learning with auxiliary tasks | Physics | 2 | Active |
| US10776692B2 | Continuous control with deep reinforcement learning | Physics | 2 | Active |
| US11651208B2 | Training action selection neural networks using a differentiable credit function | Physics | 1 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.