metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_1_task_3_run_id_0_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-1
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 1
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.14166667088866233 +/- 0.18945135260751206
name: Crash Count
verified: true
- type: extinguishing_trees
value: 1.041666679084301 +/- 3.059772488050604
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 5.208333283662796 +/- 15.298862328050262
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.4916666686534882 +/- 0.427405472920952
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.575 +/- 0.46665100224336487
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 654.5333339691163 +/- 369.49324566338055
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 654.5333339691163 +/- 369.49324566338055
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 19.52499990463257 +/- 10.494119202517384
name: Water Drop
verified: true
- type: water_pickup
value: 19.108333349227905 +/- 10.481433832592886
name: Water Pickup
verified: true
- type: cumulative_reward
value: 722.9217496871948 +/- 414.79654723295414
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 3 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 1
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment