metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_5_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-5
results:
- task:
type: sub-task
name: maximize_extinguished_burning_trees
task-id: 1
difficulty-id: 5
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.15833333656191825 +/- 0.19098850564751765
name: Crash Count
verified: true
- type: extinguishing_trees
value: 20.000000047683717 +/- 35.87091048765571
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 999.9999992370606 +/- 1793.545528264617
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.10000000298023223 +/- 0.244231706300354
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.925 +/- 0.24468024246479642
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 439.2000018119812 +/- 486.4487458526075
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 439.2000018119812 +/- 486.4487458526075
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 35.9416666328907 +/- 21.80430457793747
name: Water Drop
verified: true
- type: water_pickup
value: 35.77500002980232 +/- 21.714001930720748
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1192.8983428001404 +/- 1401.6480393641084
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 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 5
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment