metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_2_task_6_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-6-difficulty-2
results:
- task:
type: sub-task
name: drop_water
task-id: 6
difficulty-id: 2
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.029796552332118153 +/- 0.013558095195825941
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.3805455264635384 +/- 0.49240092917648515
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 1.9027276199311018 +/- 2.462004661948154
name: Extinguishing Trees Reward
verified: true
- type: preparing_trees
value: 182.82622451782225 +/- 11.38041138346274
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 182.82622451782225 +/- 11.38041138346274
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 0.9693701088428497 +/- 0.015894927913693367
name: Water Drop
verified: true
- type: cumulative_reward
value: 181.8419204711914 +/- 12.238550390744056
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 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 2
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment