metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_9_task_3_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-9
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 9
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: 40.43333244919777 +/- 89.55848904778
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 202.1666701555252 +/- 447.79246693057974
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.31666667088866235 +/- 0.38578544750821686
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: 889.5999923229217 +/- 798.283831409951
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 889.5999923229217 +/- 798.283831409951
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 46.18333358764649 +/- 23.596319104972988
name: Water Drop
verified: true
- type: water_pickup
value: 45.63333377838135 +/- 23.684241605268586
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1184.7800241470336 +/- 941.7770730791063
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 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 9
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment