metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_7_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-7
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 7
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.13333333730697633 +/- 0.1585755350905039
name: Crash Count
verified: true
- type: extinguishing_trees
value: 20.61666655242443 +/- 31.49538645519398
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 103.08333207368851 +/- 157.4769288508104
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.18333333730697632 +/- 0.31483775244365086
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: 652.3000063419342 +/- 754.7335526661299
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 652.3000063419342 +/- 754.7335526661299
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 56.241666316986084 +/- 36.06428926662349
name: Water Drop
verified: true
- type: water_pickup
value: 55.76666698455811 +/- 35.96926061643514
name: Water Pickup
verified: true
- type: cumulative_reward
value: 728.9100012302399 +/- 710.9909405090588
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 7 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 7
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment