metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_6_task_0_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-0-difficulty-6
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 6
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.09166666939854622 +/- 0.13759632868100613
name: Crash Count
verified: true
- type: extinguishing_trees
value: 32.016666914522645 +/- 54.38789961151889
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 160.08333310484886 +/- 271.9394937062471
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.21666666865348816 +/- 0.3381234780238663
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.8 +/- 0.34027852368936023
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 613.7666711807251 +/- 594.0818245118544
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 613.7666711807251 +/- 594.0818245118544
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 56.541665983200076 +/- 29.057508493771863
name: Water Drop
verified: true
- type: water_pickup
value: 56.166666412353514 +/- 29.054395046718312
name: Water Pickup
verified: true
- type: cumulative_reward
value: 885.5350048065186 +/- 571.6299167493522
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 6
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment