Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,9 @@ Training progress:
|
|
| 29 |
Numbers on X axis are average over 40 episodes, each lasting for about 500 timesteps on average. So in total the agent was trained over about 5e6 timesteps.
|
| 30 |
Learning rate decay schedule: <code>torch.optim.lr_scheduler.StepLR(opt, step_size=4000, gamma=0.7)</code>. Training code is shown in the training.py file for reference.
|
| 31 |
|
|
|
|
|
|
|
|
|
|
| 32 |
Minimal code to use the agent:</br>
|
| 33 |
```
|
| 34 |
import gym
|
|
|
|
| 29 |
Numbers on X axis are average over 40 episodes, each lasting for about 500 timesteps on average. So in total the agent was trained over about 5e6 timesteps.
|
| 30 |
Learning rate decay schedule: <code>torch.optim.lr_scheduler.StepLR(opt, step_size=4000, gamma=0.7)</code>. Training code is shown in the training.py file for reference.
|
| 31 |
|
| 32 |
+
In case video snippet does not work, here's a gif:
|
| 33 |
+
|
| 34 |
+
|
| 35 |
Minimal code to use the agent:</br>
|
| 36 |
```
|
| 37 |
import gym
|