metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_1_task_2_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-2-difficulty-1
results:
- task:
type: sub-task
name: maximize_preparing_non_burning_trees
task-id: 2
difficulty-id: 1
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.10833333656191826 +/- 0.13545462085140364
name: Crash Count
verified: true
- type: extinguishing_trees
value: 12.764999979734421 +/- 20.904079059070074
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 63.82500011920929 +/- 104.52039570112963
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.46333333626389506 +/- 0.3753984235292453
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.7550000011920929 +/- 0.37763111996880777
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 561.5350036621094 +/- 325.15177018123586
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 2807.674984741211 +/- 1625.7588563088673
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 19.77666656970978 +/- 9.682256516548964
name: Water Drop
verified: true
- type: water_pickup
value: 19.191666650772095 +/- 9.573244118078943
name: Water Pickup
verified: true
- type: cumulative_reward
value: 3287.165838623047 +/- 1376.9107350360173
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 1
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment