metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_9_task_2_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-2-difficulty-9
results:
- task:
type: sub-task
name: maximize_preparing_non_burning_trees
task-id: 2
difficulty-id: 9
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.09166666939854622 +/- 0.18317377972526547
name: Crash Count
verified: true
- type: extinguishing_trees
value: 8.949999886751176 +/- 12.562137901097202
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 44.75000040531158 +/- 62.81068995864626
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.3500000022351742 +/- 0.4114586818171751
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: 652.12500230968 +/- 512.4888000138135
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 3260.6250272393227 +/- 2562.444032266141
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 65.37499959468842 +/- 34.89231000298373
name: Water Drop
verified: true
- type: water_pickup
value: 64.99166650772095 +/- 34.92349427276053
name: Water Pickup
verified: true
- type: cumulative_reward
value: 3682.374974441528 +/- 2239.4285326262125
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 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 9
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment