metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_7_task_3_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-7
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 7
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.06666666865348816 +/- 0.12565617623235442
name: Crash Count
verified: true
- type: extinguishing_trees
value: 7.908333319425583 +/- 16.36833652069324
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 39.541666293144225 +/- 81.84168247486198
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.25000000223517416 +/- 0.37658049139486893
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.975 +/- 0.11180339887498947
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 509.2750062227249 +/- 625.6526270127268
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 509.2750062227249 +/- 625.6526270127268
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 62.22499976158142 +/- 27.943513820272507
name: Water Drop
verified: true
- type: water_pickup
value: 61.808333253860475 +/- 27.991450221952636
name: Water Pickup
verified: true
- type: cumulative_reward
value: 622.9698296546936 +/- 494.1472072826427
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 3 with difficulty 7 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 7
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment