Regularization
Entropy Regularization
Introduced by Mnih et al. in Asynchronous Methods for Deep Reinforcement LearningEntropy Regularization is a type of regularization used in reinforcement learning. For on-policy policy gradient based methods like A3C, the same mutual reinforcement behaviour leads to a highly-peaked $\pi\left(a\mid{s}\right)$ towards a few actions or action sequences, since it is easier for the actor and critic to overoptimise to a small portion of the environment. To reduce this problem, entropy regularization adds an entropy term to the loss to promote action diversity:
$$H(X) = -\sum\pi\left(x\right)\log\left(\pi\left(x\right)\right) $$
Image Credit: Wikipedia
Source: Asynchronous Methods for Deep Reinforcement Learning
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Autonomous Driving | 123 | 11.91% |
| Reinforcement Learning (RL) | 99 | 9.58% |
| Reinforcement Learning | 87 | 8.42% |
| Deep Reinforcement Learning | 61 | 5.91% |
| Autonomous Vehicles | 44 | 4.26% |
| Decision Making | 41 | 3.97% |
| Language Modelling | 29 | 2.81% |
| Imitation Learning | 23 | 2.23% |
| Object Detection | 21 | 2.03% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
