metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_10_task_2_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-2-difficulty-10
results:
- task:
type: sub-task
name: maximize_preparing_non_burning_trees
task-id: 2
difficulty-id: 10
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.15833333730697632 +/- 0.20572934499076767
name: Crash Count
verified: true
- type: extinguishing_trees
value: 19.241666620969774 +/- 33.273080342427235
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 96.20833342075348 +/- 166.36540223877446
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.20833333507180213 +/- 0.32387908421054906
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: 995.8083220481873 +/- 896.6925434987216
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 4979.041623306274 +/- 4483.462788982591
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 36.908333444595335 +/- 20.718840949931526
name: Water Drop
verified: true
- type: water_pickup
value: 36.41666669845581 +/- 20.746415247545407
name: Water Pickup
verified: true
- type: cumulative_reward
value: 5726.971720504761 +/- 3142.936334111313
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 10 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 10
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment