metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_3_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-3
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 3
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.0833333358168602 +/- 0.12681432215480823
name: Crash Count
verified: true
- type: extinguishing_trees
value: 6.791666813194752 +/- 17.30909921307683
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 33.95833272337914 +/- 86.54549141729059
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.3250000037252903 +/- 0.372579912027151
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.85 +/- 0.3284733426658932
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 1214.2916635513307 +/- 909.8089264585527
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 1214.2916635513307 +/- 909.8089264585527
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 20.291666793823243 +/- 8.402323759531772
name: Water Drop
verified: true
- type: water_pickup
value: 19.79166646003723 +/- 8.33067930580936
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1321.465838623047 +/- 654.5775149733734
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 3 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 3
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment