metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_3_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-3
results:
- task:
type: sub-task
name: maximize_extinguished_burning_trees
task-id: 1
difficulty-id: 3
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.3388888955116272 +/- 0.28207207032208675
name: Crash Count
verified: true
- type: extinguishing_trees
value: 16.488888897374274 +/- 25.98319189651514
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 824.4444324493409 +/- 1299.1595474984952
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.1083333358168602 +/- 0.1970172357255564
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.716666667163372 +/- 0.4192028074228474
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 654.4472227096558 +/- 552.5331585615204
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 654.4472227096558 +/- 552.5331585615204
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 38.655555725097656 +/- 17.813019068968373
name: Water Drop
verified: true
- type: water_pickup
value: 38.36388869285584 +/- 17.753789101902516
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1660.678343963623 +/- 2522.553744525116
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 3 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 3
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment