metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_1_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-1
results:
- task:
type: sub-task
name: maximize_extinguished_burning_trees
task-id: 1
difficulty-id: 1
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.10555555783212185 +/- 0.16411299281130134
name: Crash Count
verified: true
- type: extinguishing_trees
value: 5.788888883590698 +/- 10.994661682099375
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 289.44444465637207 +/- 549.7330871286864
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.36388889104127886 +/- 0.42710131135604623
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.7083333343267441 +/- 0.40780040400115103
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 556.8888899803162 +/- 429.9611601706457
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 556.8888899803162 +/- 429.9611601706457
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 15.513888931274414 +/- 8.362694438094918
name: Water Drop
verified: true
- type: water_pickup
value: 14.897222208976746 +/- 8.362974150430102
name: Water Pickup
verified: true
- type: cumulative_reward
value: 817.7808405578137 +/- 571.7617652663462
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 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 1
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment