metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_5_task_3_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-5
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 5
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.10000000298023223 +/- 0.14709666274350333
name: Crash Count
verified: true
- type: extinguishing_trees
value: 21.849999871850013 +/- 26.55595966139508
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 109.25000078678131 +/- 132.77980124383632
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.2833333373069763 +/- 0.3903065252105535
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: 720.8999999046325 +/- 714.1611892677554
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 720.8999999046325 +/- 714.1611892677554
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 43.80000042915344 +/- 23.772717959813576
name: Water Drop
verified: true
- type: water_pickup
value: 43.35833301544189 +/- 23.80096972956163
name: Water Pickup
verified: true
- type: cumulative_reward
value: 972.7084733963013 +/- 771.3352656170343
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 3 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 5
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment