# RL

## 1

Define the following properties of the FishingDerbyRL MDP:
- State Space S: The total number of states of the environment (which is represented by a grid world).
- Action Space A: All possible actions carried by the diver.

## 4.1
1. Not improving/learning

$\alpha = 1$ and $\alpha = 0$

2. High variance but fast learning

High $\alpha < 1$

3. Low variance and high long-term return

Low $\alpha$, high $\gamma$

4. High variance and high long-term return

High $\alpha$, high $\gamma$