On-Policy TD Control
Sarsa
Sarsa is an on-policy TD control algorithm:
$$Q\left(S_{t}, A_{t}\right) \leftarrow Q\left(S_{t}, A_{t}\right) + \alpha\left[R_{t+1} + \gamma{Q}\left(S_{t+1}, A_{t+1}\right) - Q\left(S_{t}, A_{t}\right)\right] $$
This update is done after every transition from a nonterminal state $S_{t}$. if $S_{t+1}$ is terminal, then $Q\left(S_{t+1}, A_{t+1}\right)$ is defined as zero.
To design an on-policy control algorithm using Sarsa, we estimate $q_{\pi}$ for a behaviour policy $\pi$ and then change $\pi$ towards greediness with respect to $q_{\pi}$.
Source: Sutton and Barto, Reinforcement Learning, 2nd Edition
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Reinforcement Learning (RL) | 33 | 55.00% |
| OpenAI Gym | 3 | 5.00% |
| Decision Making | 3 | 5.00% |
| Continuous Control | 3 | 5.00% |
| Combinatorial Optimization | 2 | 3.33% |
| Management | 2 | 3.33% |
| Classification | 1 | 1.67% |
| Autonomous Driving | 1 | 1.67% |
| Board Games | 1 | 1.67% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
