Upload 15 files
Browse files- Agent.onnx +3 -0
- Agent/Agent-1498206.onnx +3 -0
- Agent/Agent-1498206.pt +3 -0
- Agent/Agent-1803105.onnx +3 -0
- Agent/Agent-1803105.pt +3 -0
- Agent/Agent-499780.onnx +3 -0
- Agent/Agent-499780.pt +3 -0
- Agent/Agent-999420.onnx +3 -0
- Agent/Agent-999420.pt +3 -0
- Agent/checkpoint.pt +3 -0
- Agent/events.out.tfevents.1717484418.RICHARD.25192.0 +3 -0
- README.md +74 -0
- configuration.yaml +94 -0
- run_logs/timers.json +527 -0
- run_logs/training_status.json +62 -0
Agent.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ceb7a9ec11276a110ee2164b36d3b75052ec0e09695d2fd2958e2b64c2cb11c8
|
3 |
+
size 883467
|
Agent/Agent-1498206.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4f1f598f3ab883e15a387fc55bdb82f9e7dead62ea7a879048719931a0c573f
|
3 |
+
size 883467
|
Agent/Agent-1498206.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f9ef4108528e88f6c5377ba0f9b035b37bc8ab09ba49f632c75feecbf061718
|
3 |
+
size 5302191
|
Agent/Agent-1803105.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ceb7a9ec11276a110ee2164b36d3b75052ec0e09695d2fd2958e2b64c2cb11c8
|
3 |
+
size 883467
|
Agent/Agent-1803105.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:793ca953dafd3794c8be63487007ee4cbf98a28a50ba07bbfebe4aa9aa7ad9b0
|
3 |
+
size 5302191
|
Agent/Agent-499780.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:424d1a5c00fe295a5a84d7d3c9f4d8d8f45db2e20f4a6ace1892fad851922639
|
3 |
+
size 883467
|
Agent/Agent-499780.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:163d7f2df8afe4e19b5544027593a5053237d9673772c4e4e0f850994e5cef31
|
3 |
+
size 5302191
|
Agent/Agent-999420.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:568638fece575178b34eb3fc3c633d7ed81c10a85831daea1a8ff5dfdc9d93c7
|
3 |
+
size 883467
|
Agent/Agent-999420.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:843b0ff83250eda6bf592c689b86862da441fadc8691f342f5e59b31b6728a10
|
3 |
+
size 5302191
|
Agent/checkpoint.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:793ca953dafd3794c8be63487007ee4cbf98a28a50ba07bbfebe4aa9aa7ad9b0
|
3 |
+
size 5302191
|
Agent/events.out.tfevents.1717484418.RICHARD.25192.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeb79fa965134db11da7fe810fa4b09b7379c8784040f46d3ac5f190cb30fd9a
|
3 |
+
size 1714738
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: hivex
|
3 |
+
original_train_name: AerialWildfireSuppression_difficulty_8_task_3_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-3-difficulty-8
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
type: sub-task
|
14 |
+
name: minimize_time_fire_burning
|
15 |
+
task-id: 3
|
16 |
+
difficulty-id: 8
|
17 |
+
dataset:
|
18 |
+
name: hivex-aerial-wildfire-suppression
|
19 |
+
type: hivex-aerial-wildfire-suppression
|
20 |
+
metrics:
|
21 |
+
- type: crash_count
|
22 |
+
value: 0.11666667014360428 +/- 0.15389675739925376
|
23 |
+
name: Crash Count
|
24 |
+
verified: true
|
25 |
+
- type: extinguishing_trees
|
26 |
+
value: 7.149999964237213 +/- 12.380174144905482
|
27 |
+
name: Extinguishing Trees
|
28 |
+
verified: true
|
29 |
+
- type: extinguishing_trees_reward
|
30 |
+
value: 35.749999809265134 +/- 61.900870510137494
|
31 |
+
name: Extinguishing Trees Reward
|
32 |
+
verified: true
|
33 |
+
- type: fire_out
|
34 |
+
value: 0.2750000037252903 +/- 0.30240266233230134
|
35 |
+
name: Fire Out
|
36 |
+
verified: true
|
37 |
+
- type: fire_too_close_to_city
|
38 |
+
value: 0.975 +/- 0.11180339887498947
|
39 |
+
name: Fire too Close to City
|
40 |
+
verified: true
|
41 |
+
- type: preparing_trees
|
42 |
+
value: 637.5249996185303 +/- 610.8152897953913
|
43 |
+
name: Preparing Trees
|
44 |
+
verified: true
|
45 |
+
- type: preparing_trees_reward
|
46 |
+
value: 637.5249996185303 +/- 610.8152897953913
|
47 |
+
name: Preparing Trees Reward
|
48 |
+
verified: true
|
49 |
+
- type: water_drop
|
50 |
+
value: 62.60833292007446 +/- 40.706273365657445
|
51 |
+
name: Water Drop
|
52 |
+
verified: true
|
53 |
+
- type: water_pickup
|
54 |
+
value: 62.24166722297669 +/- 40.64510829090928
|
55 |
+
name: Water Pickup
|
56 |
+
verified: true
|
57 |
+
- type: cumulative_reward
|
58 |
+
value: 719.1452117919922 +/- 472.4957273514114
|
59 |
+
name: Cumulative Reward
|
60 |
+
verified: true
|
61 |
+
---
|
62 |
+
|
63 |
+
This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>3</code> with difficulty <code>8</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
|
64 |
+
|
65 |
+
Environment: **Aerial Wildfire Suppression**<br>
|
66 |
+
Task: <code>3</code><br>
|
67 |
+
Difficulty: <code>8</code><br>
|
68 |
+
Algorithm: <code>PPO</code><br>
|
69 |
+
Episode Length: <code>3000</code><br>
|
70 |
+
Training <code>max_steps</code>: <code>1800000</code><br>
|
71 |
+
Testing <code>max_steps</code>: <code>180000</code><br><br>
|
72 |
+
|
73 |
+
Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
|
74 |
+
Download the [Environment](https://github.com/hivex-research/hivex-environments)
|
configuration.yaml
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
default_settings: null
|
2 |
+
behaviors:
|
3 |
+
Agent:
|
4 |
+
trainer_type: ppo
|
5 |
+
hyperparameters:
|
6 |
+
batch_size: 256
|
7 |
+
buffer_size: 4096
|
8 |
+
learning_rate: 0.0003
|
9 |
+
beta: 0.005
|
10 |
+
epsilon: 0.2
|
11 |
+
lambd: 0.95
|
12 |
+
num_epoch: 3
|
13 |
+
shared_critic: false
|
14 |
+
learning_rate_schedule: linear
|
15 |
+
beta_schedule: linear
|
16 |
+
epsilon_schedule: linear
|
17 |
+
network_settings:
|
18 |
+
normalize: false
|
19 |
+
hidden_units: 256
|
20 |
+
num_layers: 2
|
21 |
+
vis_encode_type: simple
|
22 |
+
memory: null
|
23 |
+
goal_conditioning_type: hyper
|
24 |
+
deterministic: false
|
25 |
+
reward_signals:
|
26 |
+
extrinsic:
|
27 |
+
gamma: 0.995
|
28 |
+
strength: 1.0
|
29 |
+
network_settings:
|
30 |
+
normalize: false
|
31 |
+
hidden_units: 128
|
32 |
+
num_layers: 2
|
33 |
+
vis_encode_type: simple
|
34 |
+
memory: null
|
35 |
+
goal_conditioning_type: hyper
|
36 |
+
deterministic: false
|
37 |
+
init_path: null
|
38 |
+
keep_checkpoints: 5
|
39 |
+
checkpoint_interval: 500000
|
40 |
+
max_steps: 1800000
|
41 |
+
time_horizon: 4096
|
42 |
+
summary_freq: 9000
|
43 |
+
threaded: true
|
44 |
+
self_play: null
|
45 |
+
behavioral_cloning: null
|
46 |
+
env_settings:
|
47 |
+
env_path: c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/dev_environments/Hivex_AerialWildfireSuppression_win
|
48 |
+
env_args: null
|
49 |
+
base_port: 5009
|
50 |
+
num_envs: 1
|
51 |
+
num_areas: 1
|
52 |
+
seed: 5000
|
53 |
+
max_lifetime_restarts: 10
|
54 |
+
restarts_rate_limit_n: 1
|
55 |
+
restarts_rate_limit_period_s: 60
|
56 |
+
engine_settings:
|
57 |
+
width: 84
|
58 |
+
height: 84
|
59 |
+
quality_level: 5
|
60 |
+
time_scale: 20
|
61 |
+
target_frame_rate: -1
|
62 |
+
capture_frame_rate: 60
|
63 |
+
no_graphics: true
|
64 |
+
environment_parameters:
|
65 |
+
difficulty:
|
66 |
+
curriculum:
|
67 |
+
- value:
|
68 |
+
sampler_type: constant
|
69 |
+
sampler_parameters:
|
70 |
+
seed: 5000
|
71 |
+
value: 8
|
72 |
+
name: difficulty
|
73 |
+
completion_criteria: null
|
74 |
+
task:
|
75 |
+
curriculum:
|
76 |
+
- value:
|
77 |
+
sampler_type: constant
|
78 |
+
sampler_parameters:
|
79 |
+
seed: 5001
|
80 |
+
value: 3
|
81 |
+
name: task
|
82 |
+
completion_criteria: null
|
83 |
+
checkpoint_settings:
|
84 |
+
run_id: AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train
|
85 |
+
initialize_from: null
|
86 |
+
load_model: false
|
87 |
+
resume: false
|
88 |
+
force: false
|
89 |
+
train_model: false
|
90 |
+
inference: false
|
91 |
+
results_dir: results
|
92 |
+
torch_settings:
|
93 |
+
device: null
|
94 |
+
debug: false
|
run_logs/timers.json
ADDED
@@ -0,0 +1,527 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"name": "root",
|
3 |
+
"gauges": {
|
4 |
+
"Agent.Policy.Entropy.mean": {
|
5 |
+
"value": 1.3896015882492065,
|
6 |
+
"min": 1.3895232677459717,
|
7 |
+
"max": 1.461533546447754,
|
8 |
+
"count": 200
|
9 |
+
},
|
10 |
+
"Agent.Policy.Entropy.sum": {
|
11 |
+
"value": 7933.2353515625,
|
12 |
+
"min": 1081.288818359375,
|
13 |
+
"max": 24516.642578125,
|
14 |
+
"count": 200
|
15 |
+
},
|
16 |
+
"Agent.AerialWildfireSuppression.WaterDrop.mean": {
|
17 |
+
"value": 61.0,
|
18 |
+
"min": 0.3333333333333333,
|
19 |
+
"max": 176.66666666666666,
|
20 |
+
"count": 200
|
21 |
+
},
|
22 |
+
"Agent.AerialWildfireSuppression.WaterDrop.sum": {
|
23 |
+
"value": 183.0,
|
24 |
+
"min": 1.0,
|
25 |
+
"max": 922.0,
|
26 |
+
"count": 200
|
27 |
+
},
|
28 |
+
"Agent.AerialWildfireSuppression.WaterPickup.mean": {
|
29 |
+
"value": 60.666666666666664,
|
30 |
+
"min": 0.0,
|
31 |
+
"max": 175.66666666666666,
|
32 |
+
"count": 200
|
33 |
+
},
|
34 |
+
"Agent.AerialWildfireSuppression.WaterPickup.sum": {
|
35 |
+
"value": 182.0,
|
36 |
+
"min": 0.0,
|
37 |
+
"max": 921.0,
|
38 |
+
"count": 200
|
39 |
+
},
|
40 |
+
"Agent.AerialWildfireSuppression.PreparingTreesReward.mean": {
|
41 |
+
"value": 19.666666666666668,
|
42 |
+
"min": 0.0,
|
43 |
+
"max": 2220.0,
|
44 |
+
"count": 200
|
45 |
+
},
|
46 |
+
"Agent.AerialWildfireSuppression.PreparingTreesReward.sum": {
|
47 |
+
"value": 59.0,
|
48 |
+
"min": 0.0,
|
49 |
+
"max": 11000.0,
|
50 |
+
"count": 200
|
51 |
+
},
|
52 |
+
"Agent.AerialWildfireSuppression.PreparingTrees.mean": {
|
53 |
+
"value": 19.666666666666668,
|
54 |
+
"min": 0.0,
|
55 |
+
"max": 2220.0,
|
56 |
+
"count": 200
|
57 |
+
},
|
58 |
+
"Agent.AerialWildfireSuppression.PreparingTrees.sum": {
|
59 |
+
"value": 59.0,
|
60 |
+
"min": 0.0,
|
61 |
+
"max": 11000.0,
|
62 |
+
"count": 200
|
63 |
+
},
|
64 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTreesReward.mean": {
|
65 |
+
"value": 0.0,
|
66 |
+
"min": 0.0,
|
67 |
+
"max": 840.0,
|
68 |
+
"count": 200
|
69 |
+
},
|
70 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTreesReward.sum": {
|
71 |
+
"value": 0.0,
|
72 |
+
"min": 0.0,
|
73 |
+
"max": 3330.0,
|
74 |
+
"count": 200
|
75 |
+
},
|
76 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTrees.mean": {
|
77 |
+
"value": 0.0,
|
78 |
+
"min": 0.0,
|
79 |
+
"max": 168.0,
|
80 |
+
"count": 200
|
81 |
+
},
|
82 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTrees.sum": {
|
83 |
+
"value": 0.0,
|
84 |
+
"min": 0.0,
|
85 |
+
"max": 666.0,
|
86 |
+
"count": 200
|
87 |
+
},
|
88 |
+
"Agent.AerialWildfireSuppression.FireOut.mean": {
|
89 |
+
"value": 1.0,
|
90 |
+
"min": 0.0,
|
91 |
+
"max": 1.0,
|
92 |
+
"count": 200
|
93 |
+
},
|
94 |
+
"Agent.AerialWildfireSuppression.FireOut.sum": {
|
95 |
+
"value": 3.0,
|
96 |
+
"min": 0.0,
|
97 |
+
"max": 3.0,
|
98 |
+
"count": 200
|
99 |
+
},
|
100 |
+
"Agent.AerialWildfireSuppression.FiretooClosetoCity.mean": {
|
101 |
+
"value": 1.0,
|
102 |
+
"min": 0.0,
|
103 |
+
"max": 1.0,
|
104 |
+
"count": 200
|
105 |
+
},
|
106 |
+
"Agent.AerialWildfireSuppression.FiretooClosetoCity.sum": {
|
107 |
+
"value": 3.0,
|
108 |
+
"min": 0.0,
|
109 |
+
"max": 9.0,
|
110 |
+
"count": 200
|
111 |
+
},
|
112 |
+
"Agent.AerialWildfireSuppression.CrashCount.mean": {
|
113 |
+
"value": 0.0,
|
114 |
+
"min": 0.0,
|
115 |
+
"max": 1.0,
|
116 |
+
"count": 200
|
117 |
+
},
|
118 |
+
"Agent.AerialWildfireSuppression.CrashCount.sum": {
|
119 |
+
"value": 0.0,
|
120 |
+
"min": 0.0,
|
121 |
+
"max": 36.0,
|
122 |
+
"count": 200
|
123 |
+
},
|
124 |
+
"Agent.Environment.LessonNumber.difficulty.mean": {
|
125 |
+
"value": 0.0,
|
126 |
+
"min": 0.0,
|
127 |
+
"max": 0.0,
|
128 |
+
"count": 200
|
129 |
+
},
|
130 |
+
"Agent.Environment.LessonNumber.difficulty.sum": {
|
131 |
+
"value": 0.0,
|
132 |
+
"min": 0.0,
|
133 |
+
"max": 0.0,
|
134 |
+
"count": 200
|
135 |
+
},
|
136 |
+
"Agent.Environment.LessonNumber.task.mean": {
|
137 |
+
"value": 0.0,
|
138 |
+
"min": 0.0,
|
139 |
+
"max": 0.0,
|
140 |
+
"count": 200
|
141 |
+
},
|
142 |
+
"Agent.Environment.LessonNumber.task.sum": {
|
143 |
+
"value": 0.0,
|
144 |
+
"min": 0.0,
|
145 |
+
"max": 0.0,
|
146 |
+
"count": 200
|
147 |
+
},
|
148 |
+
"Agent.Environment.EpisodeLength.mean": {
|
149 |
+
"value": 1899.0,
|
150 |
+
"min": 199.0,
|
151 |
+
"max": 2999.0,
|
152 |
+
"count": 200
|
153 |
+
},
|
154 |
+
"Agent.Environment.EpisodeLength.sum": {
|
155 |
+
"value": 5697.0,
|
156 |
+
"min": 597.0,
|
157 |
+
"max": 17064.0,
|
158 |
+
"count": 200
|
159 |
+
},
|
160 |
+
"Agent.Step.mean": {
|
161 |
+
"value": 1799305.0,
|
162 |
+
"min": 8790.0,
|
163 |
+
"max": 1799305.0,
|
164 |
+
"count": 200
|
165 |
+
},
|
166 |
+
"Agent.Step.sum": {
|
167 |
+
"value": 1799305.0,
|
168 |
+
"min": 8790.0,
|
169 |
+
"max": 1799305.0,
|
170 |
+
"count": 200
|
171 |
+
},
|
172 |
+
"Agent.Policy.ExtrinsicValueEstimate.mean": {
|
173 |
+
"value": 62.46917724609375,
|
174 |
+
"min": -3.0188639163970947,
|
175 |
+
"max": 107.7006607055664,
|
176 |
+
"count": 200
|
177 |
+
},
|
178 |
+
"Agent.Policy.ExtrinsicValueEstimate.sum": {
|
179 |
+
"value": 249.876708984375,
|
180 |
+
"min": -81.50932312011719,
|
181 |
+
"max": 740.9142456054688,
|
182 |
+
"count": 200
|
183 |
+
},
|
184 |
+
"Agent.Environment.CumulativeReward.mean": {
|
185 |
+
"value": 1265.7915496826172,
|
186 |
+
"min": -37.945560455322266,
|
187 |
+
"max": 2517.000203450521,
|
188 |
+
"count": 200
|
189 |
+
},
|
190 |
+
"Agent.Environment.CumulativeReward.sum": {
|
191 |
+
"value": 5063.166198730469,
|
192 |
+
"min": -154.83996391296387,
|
193 |
+
"max": 7551.0006103515625,
|
194 |
+
"count": 200
|
195 |
+
},
|
196 |
+
"Agent.Policy.ExtrinsicReward.mean": {
|
197 |
+
"value": 1265.7915496826172,
|
198 |
+
"min": -37.945560455322266,
|
199 |
+
"max": 2517.000203450521,
|
200 |
+
"count": 200
|
201 |
+
},
|
202 |
+
"Agent.Policy.ExtrinsicReward.sum": {
|
203 |
+
"value": 5063.166198730469,
|
204 |
+
"min": -154.83996391296387,
|
205 |
+
"max": 7551.0006103515625,
|
206 |
+
"count": 200
|
207 |
+
},
|
208 |
+
"Agent.Losses.PolicyLoss.mean": {
|
209 |
+
"value": 0.04730230649667127,
|
210 |
+
"min": 0.03433962796947786,
|
211 |
+
"max": 0.05868189014494419,
|
212 |
+
"count": 188
|
213 |
+
},
|
214 |
+
"Agent.Losses.PolicyLoss.sum": {
|
215 |
+
"value": 0.04730230649667127,
|
216 |
+
"min": 0.03433962796947786,
|
217 |
+
"max": 0.1112911865018642,
|
218 |
+
"count": 188
|
219 |
+
},
|
220 |
+
"Agent.Losses.ValueLoss.mean": {
|
221 |
+
"value": 989.1805726550874,
|
222 |
+
"min": 20.165081392583392,
|
223 |
+
"max": 3212.520077369327,
|
224 |
+
"count": 188
|
225 |
+
},
|
226 |
+
"Agent.Losses.ValueLoss.sum": {
|
227 |
+
"value": 989.1805726550874,
|
228 |
+
"min": 24.88281074705578,
|
229 |
+
"max": 5524.74862663915,
|
230 |
+
"count": 188
|
231 |
+
},
|
232 |
+
"Agent.Policy.LearningRate.mean": {
|
233 |
+
"value": 4.325998558333356e-07,
|
234 |
+
"min": 4.325998558333356e-07,
|
235 |
+
"max": 0.0002988880003706666,
|
236 |
+
"count": 188
|
237 |
+
},
|
238 |
+
"Agent.Policy.LearningRate.sum": {
|
239 |
+
"value": 4.325998558333356e-07,
|
240 |
+
"min": 4.325998558333356e-07,
|
241 |
+
"max": 0.0005977760007413332,
|
242 |
+
"count": 188
|
243 |
+
},
|
244 |
+
"Agent.Policy.Epsilon.mean": {
|
245 |
+
"value": 0.10014416666666669,
|
246 |
+
"min": 0.10014416666666669,
|
247 |
+
"max": 0.19962933333333335,
|
248 |
+
"count": 188
|
249 |
+
},
|
250 |
+
"Agent.Policy.Epsilon.sum": {
|
251 |
+
"value": 0.10014416666666669,
|
252 |
+
"min": 0.10014416666666669,
|
253 |
+
"max": 0.3992586666666667,
|
254 |
+
"count": 188
|
255 |
+
},
|
256 |
+
"Agent.Policy.Beta.mean": {
|
257 |
+
"value": 1.719391666666671e-05,
|
258 |
+
"min": 1.719391666666671e-05,
|
259 |
+
"max": 0.004981503733333333,
|
260 |
+
"count": 188
|
261 |
+
},
|
262 |
+
"Agent.Policy.Beta.sum": {
|
263 |
+
"value": 1.719391666666671e-05,
|
264 |
+
"min": 1.719391666666671e-05,
|
265 |
+
"max": 0.009963007466666667,
|
266 |
+
"count": 188
|
267 |
+
},
|
268 |
+
"Agent.IsTraining.mean": {
|
269 |
+
"value": 1.0,
|
270 |
+
"min": 1.0,
|
271 |
+
"max": 1.0,
|
272 |
+
"count": 200
|
273 |
+
},
|
274 |
+
"Agent.IsTraining.sum": {
|
275 |
+
"value": 1.0,
|
276 |
+
"min": 1.0,
|
277 |
+
"max": 1.0,
|
278 |
+
"count": 200
|
279 |
+
}
|
280 |
+
},
|
281 |
+
"metadata": {
|
282 |
+
"timer_format_version": "0.1.0",
|
283 |
+
"start_time_seconds": "1717484417",
|
284 |
+
"python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]",
|
285 |
+
"command_line_arguments": "C:\\Users\\pdsie\\anaconda3\\envs\\mlagents20\\Scripts\\mlagents-learn c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/configs/mlagents/tmp/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train.yaml --run-id=AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train --base-port 5009",
|
286 |
+
"mlagents_version": "0.30.0",
|
287 |
+
"mlagents_envs_version": "0.30.0",
|
288 |
+
"communication_protocol_version": "1.5.0",
|
289 |
+
"pytorch_version": "1.7.1+cu110",
|
290 |
+
"numpy_version": "1.21.0",
|
291 |
+
"end_time_seconds": "1717489536"
|
292 |
+
},
|
293 |
+
"total": 5119.1922631,
|
294 |
+
"count": 1,
|
295 |
+
"self": 0.24806029999945167,
|
296 |
+
"children": {
|
297 |
+
"run_training.setup": {
|
298 |
+
"total": 0.0506799,
|
299 |
+
"count": 1,
|
300 |
+
"self": 0.0506799
|
301 |
+
},
|
302 |
+
"TrainerController.start_learning": {
|
303 |
+
"total": 5118.8935229,
|
304 |
+
"count": 1,
|
305 |
+
"self": 10.66667700004382,
|
306 |
+
"children": {
|
307 |
+
"TrainerController._reset_env": {
|
308 |
+
"total": 2.0584809,
|
309 |
+
"count": 1,
|
310 |
+
"self": 2.0584809
|
311 |
+
},
|
312 |
+
"TrainerController.advance": {
|
313 |
+
"total": 5106.105354599957,
|
314 |
+
"count": 601039,
|
315 |
+
"self": 9.47449909993793,
|
316 |
+
"children": {
|
317 |
+
"env_step": {
|
318 |
+
"total": 5096.630855500019,
|
319 |
+
"count": 601039,
|
320 |
+
"self": 2972.3729588000824,
|
321 |
+
"children": {
|
322 |
+
"SubprocessEnvManager._take_step": {
|
323 |
+
"total": 2117.6148383999516,
|
324 |
+
"count": 601039,
|
325 |
+
"self": 18.317511199841647,
|
326 |
+
"children": {
|
327 |
+
"TorchPolicy.evaluate": {
|
328 |
+
"total": 2099.29732720011,
|
329 |
+
"count": 601039,
|
330 |
+
"self": 2099.29732720011
|
331 |
+
}
|
332 |
+
}
|
333 |
+
},
|
334 |
+
"workers": {
|
335 |
+
"total": 6.643058299984862,
|
336 |
+
"count": 601039,
|
337 |
+
"self": 0.0,
|
338 |
+
"children": {
|
339 |
+
"worker_root": {
|
340 |
+
"total": 5106.805052400333,
|
341 |
+
"count": 601039,
|
342 |
+
"is_parallel": true,
|
343 |
+
"self": 2590.6345171001844,
|
344 |
+
"children": {
|
345 |
+
"steps_from_proto": {
|
346 |
+
"total": 0.006425899999999984,
|
347 |
+
"count": 1,
|
348 |
+
"is_parallel": true,
|
349 |
+
"self": 0.00010790000000038269,
|
350 |
+
"children": {
|
351 |
+
"_process_maybe_compressed_observation": {
|
352 |
+
"total": 0.006237099999999662,
|
353 |
+
"count": 2,
|
354 |
+
"is_parallel": true,
|
355 |
+
"self": 5.129999999975432e-05,
|
356 |
+
"children": {
|
357 |
+
"_observation_to_np_array": {
|
358 |
+
"total": 0.006185799999999908,
|
359 |
+
"count": 3,
|
360 |
+
"is_parallel": true,
|
361 |
+
"self": 2.879999999971794e-05,
|
362 |
+
"children": {
|
363 |
+
"process_pixels": {
|
364 |
+
"total": 0.00615700000000019,
|
365 |
+
"count": 3,
|
366 |
+
"is_parallel": true,
|
367 |
+
"self": 0.00018730000000011238,
|
368 |
+
"children": {
|
369 |
+
"image_decompress": {
|
370 |
+
"total": 0.005969700000000078,
|
371 |
+
"count": 3,
|
372 |
+
"is_parallel": true,
|
373 |
+
"self": 0.005969700000000078
|
374 |
+
}
|
375 |
+
}
|
376 |
+
}
|
377 |
+
}
|
378 |
+
}
|
379 |
+
}
|
380 |
+
},
|
381 |
+
"_process_rank_one_or_two_observation": {
|
382 |
+
"total": 8.089999999993935e-05,
|
383 |
+
"count": 2,
|
384 |
+
"is_parallel": true,
|
385 |
+
"self": 8.089999999993935e-05
|
386 |
+
}
|
387 |
+
}
|
388 |
+
},
|
389 |
+
"UnityEnvironment.step": {
|
390 |
+
"total": 2516.1641094001484,
|
391 |
+
"count": 601039,
|
392 |
+
"is_parallel": true,
|
393 |
+
"self": 29.655519999699663,
|
394 |
+
"children": {
|
395 |
+
"UnityEnvironment._generate_step_input": {
|
396 |
+
"total": 29.781311200314473,
|
397 |
+
"count": 601039,
|
398 |
+
"is_parallel": true,
|
399 |
+
"self": 29.781311200314473
|
400 |
+
},
|
401 |
+
"communicator.exchange": {
|
402 |
+
"total": 2202.074517300194,
|
403 |
+
"count": 601039,
|
404 |
+
"is_parallel": true,
|
405 |
+
"self": 2202.074517300194
|
406 |
+
},
|
407 |
+
"steps_from_proto": {
|
408 |
+
"total": 254.65276089993972,
|
409 |
+
"count": 601039,
|
410 |
+
"is_parallel": true,
|
411 |
+
"self": 54.30595649990482,
|
412 |
+
"children": {
|
413 |
+
"_process_maybe_compressed_observation": {
|
414 |
+
"total": 173.79149670004074,
|
415 |
+
"count": 1202078,
|
416 |
+
"is_parallel": true,
|
417 |
+
"self": 15.62005689990849,
|
418 |
+
"children": {
|
419 |
+
"_observation_to_np_array": {
|
420 |
+
"total": 158.17143980013225,
|
421 |
+
"count": 1804113,
|
422 |
+
"is_parallel": true,
|
423 |
+
"self": 13.7780902999273,
|
424 |
+
"children": {
|
425 |
+
"process_pixels": {
|
426 |
+
"total": 144.39334950020495,
|
427 |
+
"count": 1804113,
|
428 |
+
"is_parallel": true,
|
429 |
+
"self": 51.88255100031644,
|
430 |
+
"children": {
|
431 |
+
"image_decompress": {
|
432 |
+
"total": 92.51079849988851,
|
433 |
+
"count": 1804113,
|
434 |
+
"is_parallel": true,
|
435 |
+
"self": 92.51079849988851
|
436 |
+
}
|
437 |
+
}
|
438 |
+
}
|
439 |
+
}
|
440 |
+
}
|
441 |
+
}
|
442 |
+
},
|
443 |
+
"_process_rank_one_or_two_observation": {
|
444 |
+
"total": 26.555307699994167,
|
445 |
+
"count": 1202078,
|
446 |
+
"is_parallel": true,
|
447 |
+
"self": 26.555307699994167
|
448 |
+
}
|
449 |
+
}
|
450 |
+
}
|
451 |
+
}
|
452 |
+
}
|
453 |
+
}
|
454 |
+
}
|
455 |
+
}
|
456 |
+
}
|
457 |
+
}
|
458 |
+
}
|
459 |
+
}
|
460 |
+
},
|
461 |
+
"trainer_threads": {
|
462 |
+
"total": 3.149999974993989e-05,
|
463 |
+
"count": 1,
|
464 |
+
"self": 3.149999974993989e-05,
|
465 |
+
"children": {
|
466 |
+
"thread_root": {
|
467 |
+
"total": 0.0,
|
468 |
+
"count": 0,
|
469 |
+
"is_parallel": true,
|
470 |
+
"self": 0.0,
|
471 |
+
"children": {
|
472 |
+
"trainer_advance": {
|
473 |
+
"total": 5114.085280899863,
|
474 |
+
"count": 275281,
|
475 |
+
"is_parallel": true,
|
476 |
+
"self": 12.371020499772385,
|
477 |
+
"children": {
|
478 |
+
"process_trajectory": {
|
479 |
+
"total": 4383.7098505000895,
|
480 |
+
"count": 275281,
|
481 |
+
"is_parallel": true,
|
482 |
+
"self": 4383.390143900089,
|
483 |
+
"children": {
|
484 |
+
"RLTrainer._checkpoint": {
|
485 |
+
"total": 0.31970660000047246,
|
486 |
+
"count": 3,
|
487 |
+
"is_parallel": true,
|
488 |
+
"self": 0.31970660000047246
|
489 |
+
}
|
490 |
+
}
|
491 |
+
},
|
492 |
+
"_update_policy": {
|
493 |
+
"total": 718.004409900002,
|
494 |
+
"count": 224,
|
495 |
+
"is_parallel": true,
|
496 |
+
"self": 180.04820679995566,
|
497 |
+
"children": {
|
498 |
+
"TorchPPOOptimizer.update": {
|
499 |
+
"total": 537.9562031000463,
|
500 |
+
"count": 20814,
|
501 |
+
"is_parallel": true,
|
502 |
+
"self": 537.9562031000463
|
503 |
+
}
|
504 |
+
}
|
505 |
+
}
|
506 |
+
}
|
507 |
+
}
|
508 |
+
}
|
509 |
+
}
|
510 |
+
}
|
511 |
+
},
|
512 |
+
"TrainerController._save_models": {
|
513 |
+
"total": 0.06297889999950712,
|
514 |
+
"count": 1,
|
515 |
+
"self": 0.005868100000043341,
|
516 |
+
"children": {
|
517 |
+
"RLTrainer._checkpoint": {
|
518 |
+
"total": 0.05711079999946378,
|
519 |
+
"count": 1,
|
520 |
+
"self": 0.05711079999946378
|
521 |
+
}
|
522 |
+
}
|
523 |
+
}
|
524 |
+
}
|
525 |
+
}
|
526 |
+
}
|
527 |
+
}
|
run_logs/training_status.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"difficulty": {
|
3 |
+
"lesson_num": 0
|
4 |
+
},
|
5 |
+
"task": {
|
6 |
+
"lesson_num": 0
|
7 |
+
},
|
8 |
+
"Agent": {
|
9 |
+
"checkpoints": [
|
10 |
+
{
|
11 |
+
"steps": 499780,
|
12 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-499780.onnx",
|
13 |
+
"reward": 364.96832275390625,
|
14 |
+
"creation_time": 1717485601.815501,
|
15 |
+
"auxillary_file_paths": [
|
16 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-499780.pt"
|
17 |
+
]
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"steps": 999420,
|
21 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-999420.onnx",
|
22 |
+
"reward": 134.93703079223633,
|
23 |
+
"creation_time": 1717487051.9821992,
|
24 |
+
"auxillary_file_paths": [
|
25 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-999420.pt"
|
26 |
+
]
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"steps": 1498206,
|
30 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-1498206.onnx",
|
31 |
+
"reward": 673.0001220703125,
|
32 |
+
"creation_time": 1717488576.414475,
|
33 |
+
"auxillary_file_paths": [
|
34 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-1498206.pt"
|
35 |
+
]
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"steps": 1803105,
|
39 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-1803105.onnx",
|
40 |
+
"reward": 43.499457041422524,
|
41 |
+
"creation_time": 1717489536.0018642,
|
42 |
+
"auxillary_file_paths": [
|
43 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-1803105.pt"
|
44 |
+
]
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"final_checkpoint": {
|
48 |
+
"steps": 1803105,
|
49 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent.onnx",
|
50 |
+
"reward": 43.499457041422524,
|
51 |
+
"creation_time": 1717489536.0018642,
|
52 |
+
"auxillary_file_paths": [
|
53 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train\\Agent\\Agent-1803105.pt"
|
54 |
+
]
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"metadata": {
|
58 |
+
"stats_format_version": "0.3.0",
|
59 |
+
"mlagents_version": "0.30.0",
|
60 |
+
"torch_version": "1.7.1+cu110"
|
61 |
+
}
|
62 |
+
}
|