Remi Munos
9Patents
1h-index
22Co-inventors
43Inventor score
Filing activity: May 18, 2017 → Oct 16, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US11256990B2 | Memory-efficient backpropagation through time | Physics | 7 | Active |
| US11727264B2 | Reinforcement learning using pseudo-counts | Physics | 1 | Active |
| US11604997B2 | Training action selection neural networks using leave-one-out-updates | Physics | 1 | Active |
| US11593646B2 | Distributed training using actor-critic reinforcement learning with off-policy correction factors | Physics | 1 | Active |
| US10936949B2 | Training machine learning models using task selection policies to increase learning progress | Physics | 0 | Active |
| US11977983B2 | Noisy neural network layers with noise parameters | Physics | 0 | Active |
| US10839293B2 | Noisy neural network layers with noise parameters | Physics | 0 | Active |
| US11868894B2 | Distributed training using actor-critic reinforcement learning with off-policy correction factors | Physics | 0 | Active |
| US12299574B2 | Distributed training using actor-critic reinforcement learning with off-policy correction factors | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.