metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_8_task_0_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-0-difficulty-8
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 8
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.10833333656191826 +/- 0.14584900099920892
name: Crash Count
verified: true
- type: extinguishing_trees
value: 23.324999898672104 +/- 55.08031019150775
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 116.62500007152558 +/- 275.40155086604756
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.22500000149011612 +/- 0.3638448035924671
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.85 +/- 0.28562028528873973
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 769.4333295822144 +/- 713.797537109146
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 769.4333295822144 +/- 713.797537109146
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 42.46666691303253 +/- 16.681099284118027
name: Water Drop
verified: true
- type: water_pickup
value: 42.0666668176651 +/- 16.62014604652166
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1093.1966667175293 +/- 733.5777441210589
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 8 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 8
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment