metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_1_task_0_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-0-difficulty-1
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 1
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.4638888962566853 +/- 0.22022125290367361
name: Crash Count
verified: true
- type: extinguishing_trees
value: 4.927777701616288 +/- 10.908043339081729
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 24.638889169692995 +/- 54.54021798933507
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.16944444850087165 +/- 0.26087460404732826
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.4000000014901161 +/- 0.4060939306276508
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 466.66389350891114 +/- 226.10086599763596
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 466.66389350891114 +/- 226.10086599763596
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 6.894444406032562 +/- 3.5710508499944695
name: Water Drop
verified: true
- type: water_pickup
value: 6.702777767181397 +/- 3.5387613166964393
name: Water Pickup
verified: true
- type: cumulative_reward
value: 419.7281740188599 +/- 230.5992870123718
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 1
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment