metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_6_task_2_run_id_0_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-2-difficulty-6
results:
- task:
type: sub-task
name: maximize_preparing_non_burning_trees
task-id: 2
difficulty-id: 6
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.11666667014360428 +/- 0.18809603682131015
name: Crash Count
verified: true
- type: extinguishing_trees
value: 26.57500003799796 +/- 36.448371998578736
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 132.87500058710575 +/- 182.24186375120422
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.3166666701436043 +/- 0.4114586821666224
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.95 +/- 0.15389675281277315
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 637.158332157135 +/- 502.3677062623285
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 3185.791680145264 +/- 2511.8385615224347
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 81.89166564941407 +/- 40.19878442392626
name: Water Drop
verified: true
- type: water_pickup
value: 81.56666650772095 +/- 40.211261838762134
name: Water Pickup
verified: true
- type: cumulative_reward
value: 3751.6249725341795 +/- 3124.340359471712
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 6
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment