metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_8_task_4_run_id_0_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-4-difficulty-8
results:
- task:
type: sub-task
name: protect_village
task-id: 4
difficulty-id: 8
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.9925824165344238 +/- 0.02284823226393604
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.0949134185910225 +/- 0.27686598704684745
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 0.4745671033859253 +/- 1.3843300000675678
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.00357142873108387 +/- 0.015971914838998697
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.026685259863734247 +/- 0.042508034690655574
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 281.05667572021486 +/- 33.36053303432415
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 281.05667572021486 +/- 33.36053303432415
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 1.9489688873291016 +/- 0.2672890550666218
name: Water Drop
verified: true
- type: water_pickup
value: 1.9453974604606628 +/- 0.2713707685551629
name: Water Pickup
verified: true
- type: cumulative_reward
value: 171.03001670837403 +/- 35.59643888706601
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 8 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 8
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment