metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_2_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-2
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 2
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.17500000447034836 +/- 0.20572934505430354
name: Crash Count
verified: true
- type: extinguishing_trees
value: 11.175000129640102 +/- 18.059880604876085
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 55.874999076128006 +/- 90.29940061063385
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.28333333805203437 +/- 0.34666329618689634
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.825 +/- 0.3354101966249685
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 663.6749959468841 +/- 454.0686107184048
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 663.6749959468841 +/- 454.0686107184048
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 34.224999928474425 +/- 17.930769804240374
name: Water Drop
verified: true
- type: water_pickup
value: 33.84999995231628 +/- 17.957706990252632
name: Water Pickup
verified: true
- type: cumulative_reward
value: 749.1333358764648 +/- 395.7873496420998
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 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 2
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment