metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_6_task_1_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-1-difficulty-6
results:
- task:
type: sub-task
name: maximize_extinguished_burning_trees
task-id: 1
difficulty-id: 6
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.15000000447034836 +/- 0.20160177895130083
name: Crash Count
verified: true
- type: extinguishing_trees
value: 21.208333425223827 +/- 28.328527795039527
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 1060.4166695594788 +/- 1416.426402849315
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.17500000223517417 +/- 0.2885484972637629
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.9 +/- 0.26157418189029846
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 620.0166644275189 +/- 644.0197330961348
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 620.0166644275189 +/- 644.0197330961348
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 48.40833265781403 +/- 37.70947155566527
name: Water Drop
verified: true
- type: water_pickup
value: 48.12500007152558 +/- 37.613333288243446
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1735.4933523178101 +/- 1718.2560586121042
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 1 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 6
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment