metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_2_task_4_run_id_0_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-4-difficulty-2
results:
- task:
type: sub-task
name: protect_village
task-id: 4
difficulty-id: 2
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.9954545468091964 +/- 0.020327884646360022
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.28887686133384705 +/- 0.6787165224682201
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 1.4443842768669128 +/- 3.393582550370347
name: Extinguishing Trees Reward
verified: true
- type: fire_too_close_to_city
value: 0.023333333805203436 +/- 0.052815469164145035
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 173.5697063446045 +/- 22.599638913107242
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 173.5697063446045 +/- 22.599638913107242
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 1.2260812371969223 +/- 0.2007275933789739
name: Water Drop
verified: true
- type: water_pickup
value: 1.2260812371969223 +/- 0.2007275933789739
name: Water Pickup
verified: true
- type: cumulative_reward
value: 65.80658979415894 +/- 25.50451599293347
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 2
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment