metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_2_task_1_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-1-difficulty-2
results:
- task:
type: sub-task
name: maximize_extinguished_burning_trees
task-id: 1
difficulty-id: 2
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.5083333425223827 +/- 0.2699330882907145
name: Crash Count
verified: true
- type: extinguishing_trees
value: 4.355555608123541 +/- 6.907337205240576
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 217.77777848243713 +/- 345.36685865656506
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.03333333432674408 +/- 0.08719139656193886
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.5000000014901161 +/- 0.38616422218364055
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 390.2111080169678 +/- 226.11041224327414
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 390.2111080169678 +/- 226.11041224327414
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 6.283333307504654 +/- 3.095559538761643
name: Water Drop
verified: true
- type: water_pickup
value: 5.966666650772095 +/- 3.12197354808832
name: Water Pickup
verified: true
- type: cumulative_reward
value: 546.4062370300293 +/- 319.2706067457673
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 1 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 2
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment