metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_10_task_1_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-1-difficulty-10
results:
- task:
type: sub-task
name: maximize_extinguished_burning_trees
task-id: 1
difficulty-id: 10
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.0833333358168602 +/- 0.13786170275335063
name: Crash Count
verified: true
- type: extinguishing_trees
value: 22.591666561365127 +/- 27.403870739917945
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 1129.5833377838135 +/- 1370.1935526283442
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.3166666693985462 +/- 0.3819770073597531
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.95 +/- 0.22360679774997894
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 520.3083327770233 +/- 466.07708625352507
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 520.3083327770233 +/- 466.07708625352507
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 70.60000047683715 +/- 43.152979042955415
name: Water Drop
verified: true
- type: water_pickup
value: 70.2166657447815 +/- 43.11124175457642
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1891.3833183288575 +/- 1934.719348429914
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 1 with difficulty 10 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 10
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment