philippds commited on
Commit
09dd6f3
·
verified ·
1 Parent(s): 200abff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +68 -66
README.md CHANGED
@@ -1,66 +1,68 @@
1
- ---
2
- library_name: hivex
3
- original_train_name: AerialWildfireSuppression_difficulty_6_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-6
11
- results:
12
- - task:
13
- type: sub-task
14
- name: drop_water
15
- task-id: 6
16
- difficulty-id: 6
17
- dataset:
18
- name: hivex-aerial-wildfire-suppression
19
- type: hivex-aerial-wildfire-suppression
20
- metrics:
21
- - type: crash_count
22
- value: 0.011078277812339365 +/- 0.0043961198139685406
23
- name: Crash Count
24
- verified: true
25
- - type: extinguishing_trees
26
- value: 0.18530555460602044 +/- 0.16375919715020168
27
- name: Extinguishing Trees
28
- verified: true
29
- - type: extinguishing_trees_reward
30
- value: 0.926527788490057 +/- 0.8187960126823034
31
- name: Extinguishing Trees Reward
32
- verified: true
33
- - type: preparing_trees
34
- value: 293.15494537353516 +/- 7.732122846347472
35
- name: Preparing Trees
36
- verified: true
37
- - type: preparing_trees_reward
38
- value: 293.15494537353516 +/- 7.732122846347472
39
- name: Preparing Trees Reward
40
- verified: true
41
- - type: water_drop
42
- value: 0.9886111646890641 +/- 0.004251198123759855
43
- name: Water Drop
44
- verified: true
45
- - type: water_pickup
46
- value: 0.00013020833721384407 +/- 0.0005823093864947417
47
- name: Water Pickup
48
- verified: true
49
- - type: cumulative_reward
50
- value: 293.06024780273435 +/- 7.49949720574366
51
- name: Cumulative Reward
52
- verified: true
53
- ---
54
-
55
- This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>6</code> with difficulty <code>6</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
56
-
57
- Environment: **Aerial Wildfire Suppression**<br>
58
- Task: <code>6</code><br>
59
- Difficulty: <code>6</code><br>
60
- Algorithm: <code>PPO</code><br>
61
- Episode Length: <code>3000</code><br>
62
- Training <code>max_steps</code>: <code>1800000</code><br>
63
- Testing <code>max_steps</code>: <code>180000</code><br><br>
64
-
65
- Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
66
- Download the [Environment](https://github.com/hivex-research/hivex-environments)
 
 
 
1
+ ---
2
+ library_name: hivex
3
+ original_train_name: AerialWildfireSuppression_difficulty_6_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-6
11
+ results:
12
+ - task:
13
+ type: sub-task
14
+ name: drop_water
15
+ task-id: 6
16
+ difficulty-id: 6
17
+ dataset:
18
+ name: hivex-aerial-wildfire-suppression
19
+ type: hivex-aerial-wildfire-suppression
20
+ metrics:
21
+ - type: crash_count
22
+ value: 0.011078277812339365 +/- 0.0043961198139685406
23
+ name: Crash Count
24
+ verified: true
25
+ - type: extinguishing_trees
26
+ value: 0.18530555460602044 +/- 0.16375919715020168
27
+ name: Extinguishing Trees
28
+ verified: true
29
+ - type: extinguishing_trees_reward
30
+ value: 0.926527788490057 +/- 0.8187960126823034
31
+ name: Extinguishing Trees Reward
32
+ verified: true
33
+ - type: preparing_trees
34
+ value: 293.15494537353516 +/- 7.732122846347472
35
+ name: Preparing Trees
36
+ verified: true
37
+ - type: preparing_trees_reward
38
+ value: 293.15494537353516 +/- 7.732122846347472
39
+ name: Preparing Trees Reward
40
+ verified: true
41
+ - type: water_drop
42
+ value: 0.9886111646890641 +/- 0.004251198123759855
43
+ name: Water Drop
44
+ verified: true
45
+ - type: water_pickup
46
+ value: 0.00013020833721384407 +/- 0.0005823093864947417
47
+ name: Water Pickup
48
+ verified: true
49
+ - type: cumulative_reward
50
+ value: 293.06024780273435 +/- 7.49949720574366
51
+ name: Cumulative Reward
52
+ verified: true
53
+ ---
54
+
55
+ This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>6</code> with difficulty <code>6</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
56
+
57
+ Environment: **Aerial Wildfire Suppression**<br>
58
+ Task: <code>6</code><br>
59
+ Difficulty: <code>6</code><br>
60
+ Algorithm: <code>PPO</code><br>
61
+ Episode Length: <code>3000</code><br>
62
+ Training <code>max_steps</code>: <code>1800000</code><br>
63
+ Testing <code>max_steps</code>: <code>180000</code><br><br>
64
+
65
+ Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
66
+ Download the [Environment](https://github.com/hivex-research/hivex-environments)
67
+
68
+ [hivex-paper]: https://arxiv.org/abs/2501.04180