metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_10_task_0_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-0-difficulty-10
results:
- task:
type: main-task
name: main_task
task-id: 0
difficulty-id: 10
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.3416666768491268 +/- 0.20572934629325312
name: Crash Count
verified: true
- type: extinguishing_trees
value: 22.541666667163373 +/- 44.01873186547685
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 112.70833333134651 +/- 220.0936595589533
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.07500000223517418 +/- 0.1750104476777611
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.875 +/- 0.31933318682925255
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 674.8416697263717 +/- 544.8041855624299
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 674.8416697263717 +/- 544.8041855624299
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 49.54999938011169 +/- 18.605090713043403
name: Water Drop
verified: true
- type: water_pickup
value: 49.26666617393494 +/- 18.509156507840594
name: Water Pickup
verified: true
- type: cumulative_reward
value: 880.1708267211914 +/- 503.11196457140045
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 10 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 10
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment