Upload 15 files
Browse files- Agent.onnx +3 -0
- Agent/Agent-1499989.onnx +3 -0
- Agent/Agent-1499989.pt +3 -0
- Agent/Agent-1800195.onnx +3 -0
- Agent/Agent-1800195.pt +3 -0
- Agent/Agent-499953.onnx +3 -0
- Agent/Agent-499953.pt +3 -0
- Agent/Agent-999974.onnx +3 -0
- Agent/Agent-999974.pt +3 -0
- Agent/checkpoint.pt +3 -0
- Agent/events.out.tfevents.1717689392.RICHARD.44296.0 +3 -0
- README.md +66 -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:ad00e2ad86268753c480e33a63c19932d027f0a7dfc9d493ed814e1067ee98d4
|
3 |
+
size 883467
|
Agent/Agent-1499989.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ffcd4fff8c38bde3e640ded09046ad32bd8070d17625554f060be4f03aa8873
|
3 |
+
size 883467
|
Agent/Agent-1499989.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abd07b291d1c387b93fe782374409e0a27c7dfee41e4ff59995295c139d301a5
|
3 |
+
size 5302191
|
Agent/Agent-1800195.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad00e2ad86268753c480e33a63c19932d027f0a7dfc9d493ed814e1067ee98d4
|
3 |
+
size 883467
|
Agent/Agent-1800195.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:660914de0b32a6e5c33cc9e7f03973d1729f84b925823093887da4993d72416b
|
3 |
+
size 5302191
|
Agent/Agent-499953.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a96bde34c16211d475995da205d09c3dffe53b8c37e4f58d5d628fca6fe6780
|
3 |
+
size 883467
|
Agent/Agent-499953.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd805e89e04d847b26dfc06a33ae8edb606deab22c68431b8141180c789b2752
|
3 |
+
size 5302191
|
Agent/Agent-999974.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c27c1553e702d9b0969c22f0032991e594f581cf0442b723fc6fba34372879a
|
3 |
+
size 883467
|
Agent/Agent-999974.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f82469f0065e8de44d9781df275ce2c11c2ded6f6131a307d061c185004b5c2
|
3 |
+
size 5302191
|
Agent/checkpoint.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:660914de0b32a6e5c33cc9e7f03973d1729f84b925823093887da4993d72416b
|
3 |
+
size 5302191
|
Agent/events.out.tfevents.1717689392.RICHARD.44296.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dd1fea66ce5b04a3c400c0df7c3c2286ec7bbdcb55365dcf49a875e28d7c89b
|
3 |
+
size 2555236
|
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: hivex
|
3 |
+
original_train_name: AerialWildfireSuppression_difficulty_3_task_6_run_id_2_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-3
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
type: sub-task
|
14 |
+
name: drop_water
|
15 |
+
task-id: 6
|
16 |
+
difficulty-id: 3
|
17 |
+
dataset:
|
18 |
+
name: hivex-aerial-wildfire-suppression
|
19 |
+
type: hivex-aerial-wildfire-suppression
|
20 |
+
metrics:
|
21 |
+
- type: crash_count
|
22 |
+
value: 0.01590130275581032 +/- 0.009051027459662414
|
23 |
+
name: Crash Count
|
24 |
+
verified: true
|
25 |
+
- type: extinguishing_trees
|
26 |
+
value: 0.2118260153569281 +/- 0.3283880873127659
|
27 |
+
name: Extinguishing Trees
|
28 |
+
verified: true
|
29 |
+
- type: extinguishing_trees_reward
|
30 |
+
value: 1.0591301042586565 +/- 1.641940515491148
|
31 |
+
name: Extinguishing Trees Reward
|
32 |
+
verified: true
|
33 |
+
- type: preparing_trees
|
34 |
+
value: 234.83799896240234 +/- 10.68919451687246
|
35 |
+
name: Preparing Trees
|
36 |
+
verified: true
|
37 |
+
- type: preparing_trees_reward
|
38 |
+
value: 234.83799896240234 +/- 10.68919451687246
|
39 |
+
name: Preparing Trees Reward
|
40 |
+
verified: true
|
41 |
+
- type: water_drop
|
42 |
+
value: 0.9835368990898132 +/- 0.009798197368354513
|
43 |
+
name: Water Drop
|
44 |
+
verified: true
|
45 |
+
- type: water_pickup
|
46 |
+
value: 0.000875470065511763 +/- 0.001850762177686202
|
47 |
+
name: Water Pickup
|
48 |
+
verified: true
|
49 |
+
- type: cumulative_reward
|
50 |
+
value: 234.31187438964844 +/- 9.555234680707661
|
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>3</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>3</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)
|
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: 3
|
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: 6
|
81 |
+
name: task
|
82 |
+
completion_criteria: null
|
83 |
+
checkpoint_settings:
|
84 |
+
run_id: AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_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": 1.425987958908081,
|
6 |
+
"min": 1.4130876064300537,
|
7 |
+
"max": 1.6202850341796875,
|
8 |
+
"count": 200
|
9 |
+
},
|
10 |
+
"Agent.Policy.Entropy.sum": {
|
11 |
+
"value": 12893.783203125,
|
12 |
+
"min": 7088.68115234375,
|
13 |
+
"max": 18669.96484375,
|
14 |
+
"count": 200
|
15 |
+
},
|
16 |
+
"Agent.AerialWildfireSuppression.WaterDrop.mean": {
|
17 |
+
"value": 0.9800995024875622,
|
18 |
+
"min": 0.8804347826086957,
|
19 |
+
"max": 1.0,
|
20 |
+
"count": 200
|
21 |
+
},
|
22 |
+
"Agent.AerialWildfireSuppression.WaterDrop.sum": {
|
23 |
+
"value": 197.0,
|
24 |
+
"min": 118.0,
|
25 |
+
"max": 370.0,
|
26 |
+
"count": 200
|
27 |
+
},
|
28 |
+
"Agent.AerialWildfireSuppression.WaterPickup.mean": {
|
29 |
+
"value": 0.0,
|
30 |
+
"min": 0.0,
|
31 |
+
"max": 0.008547008547008548,
|
32 |
+
"count": 200
|
33 |
+
},
|
34 |
+
"Agent.AerialWildfireSuppression.WaterPickup.sum": {
|
35 |
+
"value": 0.0,
|
36 |
+
"min": 0.0,
|
37 |
+
"max": 2.0,
|
38 |
+
"count": 200
|
39 |
+
},
|
40 |
+
"Agent.AerialWildfireSuppression.PreparingTreesReward.mean": {
|
41 |
+
"value": 221.9452736318408,
|
42 |
+
"min": 184.31410256410257,
|
43 |
+
"max": 250.9290780141844,
|
44 |
+
"count": 200
|
45 |
+
},
|
46 |
+
"Agent.AerialWildfireSuppression.PreparingTreesReward.sum": {
|
47 |
+
"value": 44611.0,
|
48 |
+
"min": 28753.0,
|
49 |
+
"max": 89160.0,
|
50 |
+
"count": 200
|
51 |
+
},
|
52 |
+
"Agent.AerialWildfireSuppression.PreparingTrees.mean": {
|
53 |
+
"value": 221.9452736318408,
|
54 |
+
"min": 184.31410256410257,
|
55 |
+
"max": 250.9290780141844,
|
56 |
+
"count": 200
|
57 |
+
},
|
58 |
+
"Agent.AerialWildfireSuppression.PreparingTrees.sum": {
|
59 |
+
"value": 44611.0,
|
60 |
+
"min": 28753.0,
|
61 |
+
"max": 89160.0,
|
62 |
+
"count": 200
|
63 |
+
},
|
64 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTreesReward.mean": {
|
65 |
+
"value": 0.0,
|
66 |
+
"min": 0.0,
|
67 |
+
"max": 7.570921985815603,
|
68 |
+
"count": 200
|
69 |
+
},
|
70 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTreesReward.sum": {
|
71 |
+
"value": 0.0,
|
72 |
+
"min": 0.0,
|
73 |
+
"max": 2135.0,
|
74 |
+
"count": 200
|
75 |
+
},
|
76 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTrees.mean": {
|
77 |
+
"value": 0.0,
|
78 |
+
"min": 0.0,
|
79 |
+
"max": 1.5141843971631206,
|
80 |
+
"count": 200
|
81 |
+
},
|
82 |
+
"Agent.AerialWildfireSuppression.ExtinguishingTrees.sum": {
|
83 |
+
"value": 0.0,
|
84 |
+
"min": 0.0,
|
85 |
+
"max": 427.0,
|
86 |
+
"count": 200
|
87 |
+
},
|
88 |
+
"Agent.AerialWildfireSuppression.FireOut.mean": {
|
89 |
+
"value": 0.0,
|
90 |
+
"min": 0.0,
|
91 |
+
"max": 0.0,
|
92 |
+
"count": 200
|
93 |
+
},
|
94 |
+
"Agent.AerialWildfireSuppression.FireOut.sum": {
|
95 |
+
"value": 0.0,
|
96 |
+
"min": 0.0,
|
97 |
+
"max": 0.0,
|
98 |
+
"count": 200
|
99 |
+
},
|
100 |
+
"Agent.AerialWildfireSuppression.FiretooClosetoCity.mean": {
|
101 |
+
"value": 0.0,
|
102 |
+
"min": 0.0,
|
103 |
+
"max": 0.0,
|
104 |
+
"count": 200
|
105 |
+
},
|
106 |
+
"Agent.AerialWildfireSuppression.FiretooClosetoCity.sum": {
|
107 |
+
"value": 0.0,
|
108 |
+
"min": 0.0,
|
109 |
+
"max": 0.0,
|
110 |
+
"count": 200
|
111 |
+
},
|
112 |
+
"Agent.AerialWildfireSuppression.CrashCount.mean": {
|
113 |
+
"value": 0.01990049751243781,
|
114 |
+
"min": 0.0,
|
115 |
+
"max": 0.11956521739130435,
|
116 |
+
"count": 200
|
117 |
+
},
|
118 |
+
"Agent.AerialWildfireSuppression.CrashCount.sum": {
|
119 |
+
"value": 4.0,
|
120 |
+
"min": 0.0,
|
121 |
+
"max": 35.0,
|
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": 44.0,
|
150 |
+
"min": 22.68548387096774,
|
151 |
+
"max": 72.17073170731707,
|
152 |
+
"count": 200
|
153 |
+
},
|
154 |
+
"Agent.Environment.EpisodeLength.sum": {
|
155 |
+
"value": 8844.0,
|
156 |
+
"min": 4797.0,
|
157 |
+
"max": 12768.0,
|
158 |
+
"count": 200
|
159 |
+
},
|
160 |
+
"Agent.Step.mean": {
|
161 |
+
"value": 1799928.0,
|
162 |
+
"min": 8998.0,
|
163 |
+
"max": 1799928.0,
|
164 |
+
"count": 200
|
165 |
+
},
|
166 |
+
"Agent.Step.sum": {
|
167 |
+
"value": 1799928.0,
|
168 |
+
"min": 8998.0,
|
169 |
+
"max": 1799928.0,
|
170 |
+
"count": 200
|
171 |
+
},
|
172 |
+
"Agent.Policy.ExtrinsicValueEstimate.mean": {
|
173 |
+
"value": 133.42098999023438,
|
174 |
+
"min": 22.394886016845703,
|
175 |
+
"max": 159.1970977783203,
|
176 |
+
"count": 200
|
177 |
+
},
|
178 |
+
"Agent.Policy.ExtrinsicValueEstimate.sum": {
|
179 |
+
"value": 27751.56640625,
|
180 |
+
"min": 6606.4912109375,
|
181 |
+
"max": 59051.1171875,
|
182 |
+
"count": 200
|
183 |
+
},
|
184 |
+
"Agent.Environment.CumulativeReward.mean": {
|
185 |
+
"value": 221.04326923076923,
|
186 |
+
"min": 180.59493670886076,
|
187 |
+
"max": 251.87279151943463,
|
188 |
+
"count": 200
|
189 |
+
},
|
190 |
+
"Agent.Environment.CumulativeReward.sum": {
|
191 |
+
"value": 45977.0,
|
192 |
+
"min": 28534.0,
|
193 |
+
"max": 88055.0,
|
194 |
+
"count": 200
|
195 |
+
},
|
196 |
+
"Agent.Policy.ExtrinsicReward.mean": {
|
197 |
+
"value": 221.04326923076923,
|
198 |
+
"min": 180.59493670886076,
|
199 |
+
"max": 251.87279151943463,
|
200 |
+
"count": 200
|
201 |
+
},
|
202 |
+
"Agent.Policy.ExtrinsicReward.sum": {
|
203 |
+
"value": 45977.0,
|
204 |
+
"min": 28534.0,
|
205 |
+
"max": 88055.0,
|
206 |
+
"count": 200
|
207 |
+
},
|
208 |
+
"Agent.Losses.PolicyLoss.mean": {
|
209 |
+
"value": 0.05497260943543641,
|
210 |
+
"min": 0.037349688170555354,
|
211 |
+
"max": 0.058007586723154723,
|
212 |
+
"count": 200
|
213 |
+
},
|
214 |
+
"Agent.Losses.PolicyLoss.sum": {
|
215 |
+
"value": 0.10994521887087282,
|
216 |
+
"min": 0.041541630566558414,
|
217 |
+
"max": 0.16188250998190293,
|
218 |
+
"count": 200
|
219 |
+
},
|
220 |
+
"Agent.Losses.ValueLoss.mean": {
|
221 |
+
"value": 1950.3819149241726,
|
222 |
+
"min": 1396.0298406427555,
|
223 |
+
"max": 8655.855331420898,
|
224 |
+
"count": 200
|
225 |
+
},
|
226 |
+
"Agent.Losses.ValueLoss.sum": {
|
227 |
+
"value": 3900.7638298483453,
|
228 |
+
"min": 2027.0865550321691,
|
229 |
+
"max": 17311.710662841797,
|
230 |
+
"count": 200
|
231 |
+
},
|
232 |
+
"Agent.Policy.LearningRate.mean": {
|
233 |
+
"value": 4.403498532500031e-07,
|
234 |
+
"min": 4.403498532500031e-07,
|
235 |
+
"max": 0.00029896600034466663,
|
236 |
+
"count": 200
|
237 |
+
},
|
238 |
+
"Agent.Policy.LearningRate.sum": {
|
239 |
+
"value": 8.806997065000062e-07,
|
240 |
+
"min": 8.806997065000062e-07,
|
241 |
+
"max": 0.0008707455097514999,
|
242 |
+
"count": 200
|
243 |
+
},
|
244 |
+
"Agent.Policy.Epsilon.mean": {
|
245 |
+
"value": 0.10014675000000002,
|
246 |
+
"min": 0.10014675000000002,
|
247 |
+
"max": 0.19965533333333335,
|
248 |
+
"count": 200
|
249 |
+
},
|
250 |
+
"Agent.Policy.Epsilon.sum": {
|
251 |
+
"value": 0.20029350000000004,
|
252 |
+
"min": 0.13576016666666668,
|
253 |
+
"max": 0.5902485000000001,
|
254 |
+
"count": 200
|
255 |
+
},
|
256 |
+
"Agent.Policy.Beta.mean": {
|
257 |
+
"value": 1.7322825000000056e-05,
|
258 |
+
"min": 1.7322825000000056e-05,
|
259 |
+
"max": 0.004982801133333334,
|
260 |
+
"count": 200
|
261 |
+
},
|
262 |
+
"Agent.Policy.Beta.sum": {
|
263 |
+
"value": 3.464565000000011e-05,
|
264 |
+
"min": 3.464565000000011e-05,
|
265 |
+
"max": 0.014513400150000001,
|
266 |
+
"count": 200
|
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": "1717689391",
|
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_3_task_6_run_id_2_train.yaml --run-id=AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_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": "1717697063"
|
292 |
+
},
|
293 |
+
"total": 7672.2781862,
|
294 |
+
"count": 1,
|
295 |
+
"self": 7.004348800000116,
|
296 |
+
"children": {
|
297 |
+
"run_training.setup": {
|
298 |
+
"total": 0.05815800000000004,
|
299 |
+
"count": 1,
|
300 |
+
"self": 0.05815800000000004
|
301 |
+
},
|
302 |
+
"TrainerController.start_learning": {
|
303 |
+
"total": 7665.2156794,
|
304 |
+
"count": 1,
|
305 |
+
"self": 9.724962099872755,
|
306 |
+
"children": {
|
307 |
+
"TrainerController._reset_env": {
|
308 |
+
"total": 2.1854955,
|
309 |
+
"count": 1,
|
310 |
+
"self": 2.1854955
|
311 |
+
},
|
312 |
+
"TrainerController.advance": {
|
313 |
+
"total": 7653.224551900127,
|
314 |
+
"count": 600066,
|
315 |
+
"self": 9.746103100203072,
|
316 |
+
"children": {
|
317 |
+
"env_step": {
|
318 |
+
"total": 7643.478448799924,
|
319 |
+
"count": 600066,
|
320 |
+
"self": 5450.0140986000115,
|
321 |
+
"children": {
|
322 |
+
"SubprocessEnvManager._take_step": {
|
323 |
+
"total": 2186.783005899845,
|
324 |
+
"count": 600066,
|
325 |
+
"self": 18.78184609936534,
|
326 |
+
"children": {
|
327 |
+
"TorchPolicy.evaluate": {
|
328 |
+
"total": 2168.00115980048,
|
329 |
+
"count": 600066,
|
330 |
+
"self": 2168.00115980048
|
331 |
+
}
|
332 |
+
}
|
333 |
+
},
|
334 |
+
"workers": {
|
335 |
+
"total": 6.6813443000668995,
|
336 |
+
"count": 600066,
|
337 |
+
"self": 0.0,
|
338 |
+
"children": {
|
339 |
+
"worker_root": {
|
340 |
+
"total": 7651.278561199662,
|
341 |
+
"count": 600066,
|
342 |
+
"is_parallel": true,
|
343 |
+
"self": 2706.458431699766,
|
344 |
+
"children": {
|
345 |
+
"steps_from_proto": {
|
346 |
+
"total": 0.006778799999999974,
|
347 |
+
"count": 1,
|
348 |
+
"is_parallel": true,
|
349 |
+
"self": 0.0001061999999998342,
|
350 |
+
"children": {
|
351 |
+
"_process_maybe_compressed_observation": {
|
352 |
+
"total": 0.0065853999999998525,
|
353 |
+
"count": 2,
|
354 |
+
"is_parallel": true,
|
355 |
+
"self": 5.089999999974282e-05,
|
356 |
+
"children": {
|
357 |
+
"_observation_to_np_array": {
|
358 |
+
"total": 0.00653450000000011,
|
359 |
+
"count": 3,
|
360 |
+
"is_parallel": true,
|
361 |
+
"self": 2.889999999999837e-05,
|
362 |
+
"children": {
|
363 |
+
"process_pixels": {
|
364 |
+
"total": 0.006505600000000111,
|
365 |
+
"count": 3,
|
366 |
+
"is_parallel": true,
|
367 |
+
"self": 0.00017350000000004862,
|
368 |
+
"children": {
|
369 |
+
"image_decompress": {
|
370 |
+
"total": 0.006332100000000063,
|
371 |
+
"count": 3,
|
372 |
+
"is_parallel": true,
|
373 |
+
"self": 0.006332100000000063
|
374 |
+
}
|
375 |
+
}
|
376 |
+
}
|
377 |
+
}
|
378 |
+
}
|
379 |
+
}
|
380 |
+
},
|
381 |
+
"_process_rank_one_or_two_observation": {
|
382 |
+
"total": 8.720000000028705e-05,
|
383 |
+
"count": 2,
|
384 |
+
"is_parallel": true,
|
385 |
+
"self": 8.720000000028705e-05
|
386 |
+
}
|
387 |
+
}
|
388 |
+
},
|
389 |
+
"UnityEnvironment.step": {
|
390 |
+
"total": 4944.813350699897,
|
391 |
+
"count": 600066,
|
392 |
+
"is_parallel": true,
|
393 |
+
"self": 38.464186999652156,
|
394 |
+
"children": {
|
395 |
+
"UnityEnvironment._generate_step_input": {
|
396 |
+
"total": 35.085599700127574,
|
397 |
+
"count": 600066,
|
398 |
+
"is_parallel": true,
|
399 |
+
"self": 35.085599700127574
|
400 |
+
},
|
401 |
+
"communicator.exchange": {
|
402 |
+
"total": 4581.378129200245,
|
403 |
+
"count": 600066,
|
404 |
+
"is_parallel": true,
|
405 |
+
"self": 4581.378129200245
|
406 |
+
},
|
407 |
+
"steps_from_proto": {
|
408 |
+
"total": 289.88543479987214,
|
409 |
+
"count": 600066,
|
410 |
+
"is_parallel": true,
|
411 |
+
"self": 60.511119899825076,
|
412 |
+
"children": {
|
413 |
+
"_process_maybe_compressed_observation": {
|
414 |
+
"total": 199.46321310062854,
|
415 |
+
"count": 1200132,
|
416 |
+
"is_parallel": true,
|
417 |
+
"self": 18.31135770069261,
|
418 |
+
"children": {
|
419 |
+
"_observation_to_np_array": {
|
420 |
+
"total": 181.15185539993593,
|
421 |
+
"count": 1852653,
|
422 |
+
"is_parallel": true,
|
423 |
+
"self": 16.186660200145127,
|
424 |
+
"children": {
|
425 |
+
"process_pixels": {
|
426 |
+
"total": 164.9651951997908,
|
427 |
+
"count": 1852653,
|
428 |
+
"is_parallel": true,
|
429 |
+
"self": 59.95549360009309,
|
430 |
+
"children": {
|
431 |
+
"image_decompress": {
|
432 |
+
"total": 105.0097015996977,
|
433 |
+
"count": 1852653,
|
434 |
+
"is_parallel": true,
|
435 |
+
"self": 105.0097015996977
|
436 |
+
}
|
437 |
+
}
|
438 |
+
}
|
439 |
+
}
|
440 |
+
}
|
441 |
+
}
|
442 |
+
},
|
443 |
+
"_process_rank_one_or_two_observation": {
|
444 |
+
"total": 29.91110179941854,
|
445 |
+
"count": 1200132,
|
446 |
+
"is_parallel": true,
|
447 |
+
"self": 29.91110179941854
|
448 |
+
}
|
449 |
+
}
|
450 |
+
}
|
451 |
+
}
|
452 |
+
}
|
453 |
+
}
|
454 |
+
}
|
455 |
+
}
|
456 |
+
}
|
457 |
+
}
|
458 |
+
}
|
459 |
+
}
|
460 |
+
},
|
461 |
+
"trainer_threads": {
|
462 |
+
"total": 2.519999998185085e-05,
|
463 |
+
"count": 1,
|
464 |
+
"self": 2.519999998185085e-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": 7658.720798499866,
|
474 |
+
"count": 441314,
|
475 |
+
"is_parallel": true,
|
476 |
+
"self": 11.655235299772357,
|
477 |
+
"children": {
|
478 |
+
"process_trajectory": {
|
479 |
+
"total": 6843.380529000085,
|
480 |
+
"count": 441314,
|
481 |
+
"is_parallel": true,
|
482 |
+
"self": 6843.058842200085,
|
483 |
+
"children": {
|
484 |
+
"RLTrainer._checkpoint": {
|
485 |
+
"total": 0.3216867999999522,
|
486 |
+
"count": 3,
|
487 |
+
"is_parallel": true,
|
488 |
+
"self": 0.3216867999999522
|
489 |
+
}
|
490 |
+
}
|
491 |
+
},
|
492 |
+
"_update_policy": {
|
493 |
+
"total": 803.6850342000089,
|
494 |
+
"count": 423,
|
495 |
+
"is_parallel": true,
|
496 |
+
"self": 201.7709960999889,
|
497 |
+
"children": {
|
498 |
+
"TorchPPOOptimizer.update": {
|
499 |
+
"total": 601.91403810002,
|
500 |
+
"count": 20679,
|
501 |
+
"is_parallel": true,
|
502 |
+
"self": 601.91403810002
|
503 |
+
}
|
504 |
+
}
|
505 |
+
}
|
506 |
+
}
|
507 |
+
}
|
508 |
+
}
|
509 |
+
}
|
510 |
+
}
|
511 |
+
},
|
512 |
+
"TrainerController._save_models": {
|
513 |
+
"total": 0.08064470000044821,
|
514 |
+
"count": 1,
|
515 |
+
"self": 0.013150900000255206,
|
516 |
+
"children": {
|
517 |
+
"RLTrainer._checkpoint": {
|
518 |
+
"total": 0.067493800000193,
|
519 |
+
"count": 1,
|
520 |
+
"self": 0.067493800000193
|
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": 499953,
|
12 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-499953.onnx",
|
13 |
+
"reward": 213.5,
|
14 |
+
"creation_time": 1717691614.601275,
|
15 |
+
"auxillary_file_paths": [
|
16 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-499953.pt"
|
17 |
+
]
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"steps": 999974,
|
21 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-999974.onnx",
|
22 |
+
"reward": 271.390243902439,
|
23 |
+
"creation_time": 1717693710.0845063,
|
24 |
+
"auxillary_file_paths": [
|
25 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-999974.pt"
|
26 |
+
]
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"steps": 1499989,
|
30 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-1499989.onnx",
|
31 |
+
"reward": 214.56603773584905,
|
32 |
+
"creation_time": 1717695798.1366997,
|
33 |
+
"auxillary_file_paths": [
|
34 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-1499989.pt"
|
35 |
+
]
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"steps": 1800195,
|
39 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-1800195.onnx",
|
40 |
+
"reward": 156.72222222222223,
|
41 |
+
"creation_time": 1717697056.172587,
|
42 |
+
"auxillary_file_paths": [
|
43 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-1800195.pt"
|
44 |
+
]
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"final_checkpoint": {
|
48 |
+
"steps": 1800195,
|
49 |
+
"file_path": "results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent.onnx",
|
50 |
+
"reward": 156.72222222222223,
|
51 |
+
"creation_time": 1717697056.172587,
|
52 |
+
"auxillary_file_paths": [
|
53 |
+
"results\\AerialWildfireSuppression/train/AerialWildfireSuppression_difficulty_3_task_6_run_id_2_train\\Agent\\Agent-1800195.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 |
+
}
|