metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_6_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-6
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 6
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.06666666865348816 +/- 0.1134261779434835
name: Crash Count
verified: true
- type: extinguishing_trees
value: 1.5666666589677334 +/- 2.829150672657006
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 7.833333364129066 +/- 14.145753412942762
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.2666666693985462 +/- 0.33508312811569124
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.95 +/- 0.1538967528127731
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 154.78333240449427 +/- 154.1237338451524
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 154.78333240449427 +/- 154.1237338451524
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 7.933333319425583 +/- 8.128248283765428
name: Water Drop
verified: true
- type: water_pickup
value: 7.249999922513962 +/- 8.238140370843592
name: Water Pickup
verified: true
- type: cumulative_reward
value: 165.14980994462968 +/- 219.08646861162933
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 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 6
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment