Update README.md
Browse files
README.md
CHANGED
@@ -1,62 +1,64 @@
|
|
1 |
-
---
|
2 |
-
library_name: hivex
|
3 |
-
original_train_name: AerialWildfireSuppression_difficulty_1_task_6_run_id_1_train
|
4 |
-
tags:
|
5 |
-
- hivex
|
6 |
-
- hivex-aerial-wildfire-suppression
|
7 |
-
- reinforcement-learning
|
8 |
-
- multi-agent-reinforcement-learning
|
9 |
-
model-index:
|
10 |
-
- name: hivex-AWS-PPO-baseline-task-6-difficulty-1
|
11 |
-
results:
|
12 |
-
- task:
|
13 |
-
type: sub-task
|
14 |
-
name: drop_water
|
15 |
-
task-id: 6
|
16 |
-
difficulty-id: 1
|
17 |
-
dataset:
|
18 |
-
name: hivex-aerial-wildfire-suppression
|
19 |
-
type: hivex-aerial-wildfire-suppression
|
20 |
-
metrics:
|
21 |
-
- type: crash_count
|
22 |
-
value: 0.040009206905961034 +/- 0.018735561549171307
|
23 |
-
name: Crash Count
|
24 |
-
verified: true
|
25 |
-
- type: extinguishing_trees
|
26 |
-
value: 0.4969854736700654 +/- 0.6300676451261423
|
27 |
-
name: Extinguishing Trees
|
28 |
-
verified: true
|
29 |
-
- type: extinguishing_trees_reward
|
30 |
-
value: 2.484927378222346 +/- 3.150338277465211
|
31 |
-
name: Extinguishing Trees Reward
|
32 |
-
verified: true
|
33 |
-
- type: preparing_trees
|
34 |
-
value: 143.18572998046875 +/- 12.10208288767324
|
35 |
-
name: Preparing Trees
|
36 |
-
verified: true
|
37 |
-
- type: preparing_trees_reward
|
38 |
-
value: 143.18572998046875 +/- 12.10208288767324
|
39 |
-
name: Preparing Trees Reward
|
40 |
-
verified: true
|
41 |
-
- type: water_drop
|
42 |
-
value: 0.9589269667863846 +/- 0.018643650861373894
|
43 |
-
name: Water Drop
|
44 |
-
verified: true
|
45 |
-
- type: cumulative_reward
|
46 |
-
value: 141.81843147277831 +/- 13.9801382441756
|
47 |
-
name: Cumulative Reward
|
48 |
-
verified: true
|
49 |
-
---
|
50 |
-
|
51 |
-
This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>6</code> with difficulty <code>1</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
|
52 |
-
|
53 |
-
Environment: **Aerial Wildfire Suppression**<br>
|
54 |
-
Task: <code>6</code><br>
|
55 |
-
Difficulty: <code>1</code><br>
|
56 |
-
Algorithm: <code>PPO</code><br>
|
57 |
-
Episode Length: <code>3000</code><br>
|
58 |
-
Training <code>max_steps</code>: <code>1800000</code><br>
|
59 |
-
Testing <code>max_steps</code>: <code>180000</code><br><br>
|
60 |
-
|
61 |
-
Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
|
62 |
-
Download the [Environment](https://github.com/hivex-research/hivex-environments)
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: hivex
|
3 |
+
original_train_name: AerialWildfireSuppression_difficulty_1_task_6_run_id_1_train
|
4 |
+
tags:
|
5 |
+
- hivex
|
6 |
+
- hivex-aerial-wildfire-suppression
|
7 |
+
- reinforcement-learning
|
8 |
+
- multi-agent-reinforcement-learning
|
9 |
+
model-index:
|
10 |
+
- name: hivex-AWS-PPO-baseline-task-6-difficulty-1
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
type: sub-task
|
14 |
+
name: drop_water
|
15 |
+
task-id: 6
|
16 |
+
difficulty-id: 1
|
17 |
+
dataset:
|
18 |
+
name: hivex-aerial-wildfire-suppression
|
19 |
+
type: hivex-aerial-wildfire-suppression
|
20 |
+
metrics:
|
21 |
+
- type: crash_count
|
22 |
+
value: 0.040009206905961034 +/- 0.018735561549171307
|
23 |
+
name: Crash Count
|
24 |
+
verified: true
|
25 |
+
- type: extinguishing_trees
|
26 |
+
value: 0.4969854736700654 +/- 0.6300676451261423
|
27 |
+
name: Extinguishing Trees
|
28 |
+
verified: true
|
29 |
+
- type: extinguishing_trees_reward
|
30 |
+
value: 2.484927378222346 +/- 3.150338277465211
|
31 |
+
name: Extinguishing Trees Reward
|
32 |
+
verified: true
|
33 |
+
- type: preparing_trees
|
34 |
+
value: 143.18572998046875 +/- 12.10208288767324
|
35 |
+
name: Preparing Trees
|
36 |
+
verified: true
|
37 |
+
- type: preparing_trees_reward
|
38 |
+
value: 143.18572998046875 +/- 12.10208288767324
|
39 |
+
name: Preparing Trees Reward
|
40 |
+
verified: true
|
41 |
+
- type: water_drop
|
42 |
+
value: 0.9589269667863846 +/- 0.018643650861373894
|
43 |
+
name: Water Drop
|
44 |
+
verified: true
|
45 |
+
- type: cumulative_reward
|
46 |
+
value: 141.81843147277831 +/- 13.9801382441756
|
47 |
+
name: Cumulative Reward
|
48 |
+
verified: true
|
49 |
+
---
|
50 |
+
|
51 |
+
This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>6</code> with difficulty <code>1</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
|
52 |
+
|
53 |
+
Environment: **Aerial Wildfire Suppression**<br>
|
54 |
+
Task: <code>6</code><br>
|
55 |
+
Difficulty: <code>1</code><br>
|
56 |
+
Algorithm: <code>PPO</code><br>
|
57 |
+
Episode Length: <code>3000</code><br>
|
58 |
+
Training <code>max_steps</code>: <code>1800000</code><br>
|
59 |
+
Testing <code>max_steps</code>: <code>180000</code><br><br>
|
60 |
+
|
61 |
+
Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
|
62 |
+
Download the [Environment](https://github.com/hivex-research/hivex-environments)
|
63 |
+
|
64 |
+
[hivex-paper]: https://arxiv.org/abs/2501.04180
|