metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_10_task_4_run_id_0_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-4-difficulty-10
results:
- task:
type: sub-task
name: protect_village
task-id: 4
difficulty-id: 10
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.9949999988079071 +/- 0.022360685106199443
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.29754857206717134 +/- 0.6612722591280618
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 1.4877428144216538 +/- 3.3063611877410133
name: Extinguishing Trees Reward
verified: true
- type: fire_too_close_to_city
value: 0.022103730216622354 +/- 0.039482863821780616
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 274.65237579345705 +/- 34.49504850001327
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 274.65237579345705 +/- 34.49504850001327
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 2.101252889633179 +/- 0.3808157213259622
name: Water Drop
verified: true
- type: water_pickup
value: 2.101252889633179 +/- 0.3808157213259622
name: Water Pickup
verified: true
- type: cumulative_reward
value: 168.44546432495116 +/- 38.14918935961842
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 10 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 10
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment