metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_4_task_6_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-6-difficulty-4
results:
- task:
type: sub-task
name: drop_water
task-id: 6
difficulty-id: 4
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.019636338157579303 +/- 0.006296536151540525
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.20098300511017442 +/- 0.20730763026051913
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 1.0049150258302688 +/- 1.0365381477211943
name: Extinguishing Trees Reward
verified: true
- type: preparing_trees
value: 257.4399574279785 +/- 10.902792920729194
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 257.4399574279785 +/- 10.902792920729194
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 0.9798782348632813 +/- 0.007123928367457922
name: Water Drop
verified: true
- type: water_pickup
value: 0.000187265919521451 +/- 0.0008374786518379387
name: Water Pickup
verified: true
- type: cumulative_reward
value: 256.58973693847656 +/- 11.54790983559329
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 4
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment