metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_2_task_3_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-2
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 2
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.06666666865348816 +/- 0.13679711768822556
name: Crash Count
verified: true
- type: extinguishing_trees
value: 1.45 +/- 3.3495657386738666
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 7.249999952316284 +/- 16.74782867264003
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.3527777805924416 +/- 0.4007283026646903
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.716666667163372 +/- 0.4192028074228474
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 255.98055567741395 +/- 148.28355870416527
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 255.98055567741395 +/- 148.28355870416527
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 19.411111223697663 +/- 13.424328820382387
name: Water Drop
verified: true
- type: water_pickup
value: 19.355555641651154 +/- 13.43296587945375
name: Water Pickup
verified: true
- type: cumulative_reward
value: 259.08557624816893 +/- 165.96403709055332
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 3 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 2
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment