metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_6_task_6_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-6-difficulty-6
results:
- task:
type: sub-task
name: drop_water
task-id: 6
difficulty-id: 6
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.011078277812339365 +/- 0.0043961198139685406
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.18530555460602044 +/- 0.16375919715020168
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 0.926527788490057 +/- 0.8187960126823034
name: Extinguishing Trees Reward
verified: true
- type: preparing_trees
value: 293.15494537353516 +/- 7.732122846347472
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 293.15494537353516 +/- 7.732122846347472
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 0.9886111646890641 +/- 0.004251198123759855
name: Water Drop
verified: true
- type: water_pickup
value: 0.00013020833721384407 +/- 0.0005823093864947417
name: Water Pickup
verified: true
- type: cumulative_reward
value: 293.06024780273435 +/- 7.49949720574366
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 6
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment