Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
library_name: torch
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- table-2
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Card for ahalev/mcuu-table-2-hnxw35t5
|
10 |
+
|
11 |
+
This model corresponds to run(s) in Table 2, specifically that with the hyperparameters:
|
12 |
+
|
13 |
+
**1)** {'scenario': 8, 'forecast_horizon': 6, 'intrinsic_reward_weight': 0.0001, 'bound_reward_weight': 'cosine', 'noise_std': 0.01}
|
14 |
+
|
15 |
+
## Usage
|
16 |
+
```python
|
17 |
+
from trainer import Trainer
|
18 |
+
trainer = Trainer.from_pretrained('ahalev/mcuu-table-2-hnxw35t5')
|
19 |
+
algo, env = trainer.algo, trainer.env
|
20 |
+
|
21 |
+
# Get an action from a random observation
|
22 |
+
action, _ = algo.policy.get_action(env.observation_space.sample())
|
23 |
+
|
24 |
+
# Evaluate the policy over 2920 timesteps
|
25 |
+
evaluation = trainer.evaluate()
|
26 |
+
```
|
27 |
+
|
28 |
+
For more information, see the [repo](https://github.com/ahalev/Microgrid-Control-Under-Uncertainty)
|
29 |
+
and the [paper](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4866653).
|
30 |
+
|
31 |
+
This model was created by [@ahalev](https://hf.co/ahalev).
|