Non-parametric approximation of Q-values by storing all visited states and doing inference through k-Nearest Neighbors.
Source: Model-Free Episodic ControlPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Reinforcement Learning (RL) | 2 | 50.00% |
Atari Games | 1 | 25.00% |
Decision Making | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |