metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_8_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-8
results:
- task:
type: sub-task
name: maximize_extinguished_burning_trees
task-id: 1
difficulty-id: 8
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.30833334252238276 +/- 0.2771777226968141
name: Crash Count
verified: true
- type: extinguishing_trees
value: 28.216666746139527 +/- 38.8679015625057
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 1410.833318901062 +/- 1943.3950349162335
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.06666666865348816 +/- 0.16578715799245552
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: 592.4916698455811 +/- 571.7471548283543
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 592.4916698455811 +/- 571.7471548283543
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 45.858332777023314 +/- 19.358443427747147
name: Water Drop
verified: true
- type: water_pickup
value: 45.541666460037234 +/- 19.38731633910842
name: Water Pickup
verified: true
- type: cumulative_reward
value: 1881.6991638183595 +/- 1414.2531270122881
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 8 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 8
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment