metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_10_task_3_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-10
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 10
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.21666667088866234 +/- 0.25989201752505897
name: Crash Count
verified: true
- type: extinguishing_trees
value: 23.541666555404664 +/- 25.76001879059616
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 117.70833463668824 +/- 128.80009751865373
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.25000000596046446 +/- 0.3176117073446609
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.95 +/- 0.22360679774997894
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 842.3416595458984 +/- 719.565955429358
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 842.3416595458984 +/- 719.565955429358
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 56.20000038146973 +/- 35.51066867416029
name: Water Drop
verified: true
- type: water_pickup
value: 55.85000023841858 +/- 35.4871245294335
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1050.1918411254883 +/- 490.0267879628168
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 10 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 10
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment