metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_4_task_0_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-0-difficulty-4
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 4
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.26666667461395266 +/- 0.24423170630035398
name: Crash Count
verified: true
- type: extinguishing_trees
value: 24.53333340883255 +/- 44.947390538539814
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 122.66666712760926 +/- 224.73694526974205
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.14166666939854622 +/- 0.24348229211157768
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.975 +/- 0.11180339887498947
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 818.2583312273025 +/- 623.9383921347651
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 818.2583312273025 +/- 623.9383921347651
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 12.241666674613953 +/- 5.139423095979583
name: Water Drop
verified: true
- type: water_pickup
value: 11.858333373069764 +/- 5.146473016503177
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1014.383337020874 +/- 634.9201357813032
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 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 4
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment