Policy Gradient Methods
REINFORCE
REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to update the policy parameter $\theta$. Since one full trajectory must be completed to construct a sample space, it is updated as an off-policy algorithm.
$$ \nabla_{\theta}J\left(\theta\right) = \mathbb{E}_{\pi}\left[G_{t}\nabla_{\theta}\ln\pi_{\theta}\left(A_{t}\mid{S_{t}}\right)\right]$$
Image Credit: Tingwu Wang
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Reinforcement Learning (RL) | 51 | 23.83% |
| Sentence | 8 | 3.74% |
| Text Generation | 8 | 3.74% |
| Image Classification | 7 | 3.27% |
| Question Answering | 6 | 2.80% |
| Decision Making | 5 | 2.34% |
| Recommendation Systems | 5 | 2.34% |
| Image Captioning | 5 | 2.34% |
| Retrieval | 4 | 1.87% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
