metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_4_task_3_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-4
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 4
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.12500000223517418 +/- 0.17832062789523476
name: Crash Count
verified: true
- type: extinguishing_trees
value: 12.74999994635582 +/- 16.512222842027622
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 63.74999964237213 +/- 82.56111388966389
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.2833333358168602 +/- 0.3711055092960568
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.875 +/- 0.2221308291596596
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 754.1750064849854 +/- 639.6152297445449
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 754.1750064849854 +/- 639.6152297445449
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 27.541666519641876 +/- 14.354622400373676
name: Water Drop
verified: true
- type: water_pickup
value: 27.24166692495346 +/- 14.290989756251832
name: Water Pickup
verified: true
- type: cumulative_reward
value: 763.3192396879197 +/- 649.6844365742547
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 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 4
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment