metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_5_task_4_run_id_0_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-4-difficulty-5
results:
- task:
type: sub-task
name: protect_village
task-id: 4
difficulty-id: 5
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.9886904746294022 +/- 0.02771131517144696
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.08853785246610642 +/- 0.18335850809661372
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 0.4426892638206482 +/- 0.9167925407962902
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.00773809552192688 +/- 0.02389552224594306
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.008712121471762656 +/- 0.026843490782201274
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 273.38488922119143 +/- 40.98115816740078
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 273.38488922119143 +/- 40.98115816740078
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 1.757782220840454 +/- 0.286049469501929
name: Water Drop
verified: true
- type: water_pickup
value: 1.7500441253185273 +/- 0.2868768059725031
name: Water Pickup
verified: true
- type: cumulative_reward
value: 172.30555000305176 +/- 38.100567507916715
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 5
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment