metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_8_task_3_run_id_1_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-3-difficulty-8
results:
- task:
type: sub-task
name: minimize_time_fire_burning
task-id: 3
difficulty-id: 8
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.11666667014360428 +/- 0.15389675739925376
name: Crash Count
verified: true
- type: extinguishing_trees
value: 7.149999964237213 +/- 12.380174144905482
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 35.749999809265134 +/- 61.900870510137494
name: Extinguishing Trees Reward
verified: true
- type: fire_out
value: 0.2750000037252903 +/- 0.30240266233230134
name: Fire Out
verified: true
- type: fire_too_close_to_city
value: 0.975 +/- 0.11180339887498947
name: Fire too Close to City
verified: true
- type: preparing_trees
value: 637.5249996185303 +/- 610.8152897953913
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 637.5249996185303 +/- 610.8152897953913
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 62.60833292007446 +/- 40.706273365657445
name: Water Drop
verified: true
- type: water_pickup
value: 62.24166722297669 +/- 40.64510829090928
name: Water Pickup
verified: true
- type: cumulative_reward
value: 719.1452117919922 +/- 472.4957273514114
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 8
using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 8
Algorithm: PPO
Episode Length: 3000
Training max_steps
: 1800000
Testing max_steps
: 180000
Train & Test Scripts
Download the Environment