Run the agent on a single episode. Parameters ---------- max_steps : int The maximum number of steps to run an episode render : bool Whether to render the episode during training Returns ------- reward : float
(self, max_steps, render=False)
| 63 | |
| 64 | @abstractmethod |
| 65 | def run_episode(self, max_steps, render=False): |
| 66 | """ |
| 67 | Run the agent on a single episode. |
| 68 | |
| 69 | Parameters |
| 70 | ---------- |
| 71 | max_steps : int |
| 72 | The maximum number of steps to run an episode |
| 73 | render : bool |
| 74 | Whether to render the episode during training |
| 75 | |
| 76 | Returns |
| 77 | ------- |
| 78 | reward : float |
| 79 | The total reward on the episode, averaged over the theta samples. |
| 80 | steps : float |
| 81 | The total number of steps taken on the episode, averaged over the |
| 82 | theta samples. |
| 83 | """ |
| 84 | raise NotImplementedError |
| 85 | |
| 86 | @abstractmethod |
| 87 | def update(self): |