metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_1_task_4_run_id_0_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-4-difficulty-1
results:
- task:
type: sub-task
name: protect_village
task-id: 4
difficulty-id: 1
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.6166666761040688 +/- 0.22360679529482064
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.4333333492279053 +/- 1.9379256515825043
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 2.166666603088379 +/- 9.689627618168343
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.05833333507180214 +/- 0.11180340220699042
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.425 +/- 0.37257991018529735
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 210.27499961853027 +/- 101.36103492999625
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 210.27499961853027 +/- 101.36103492999625
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 3.3749999940395354 +/- 2.19507356485688
name: Water Drop
verified: true
- type: water_pickup
value: 3.2916666686534883 +/- 2.260695820449611
name: Water Pickup
verified: true
- type: cumulative_reward
value: '-69.60107120275498 +/- 211.17136032627994'
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 1
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment