metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_7_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-7
results:
- task:
type: sub-task
name: drop_water
task-id: 6
difficulty-id: 7
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.015272001700941474 +/- 0.008560343748877621
name: Crash Count
verified: true
- type: extinguishing_trees
value: 0.16764693087898194 +/- 0.19795760638271612
name: Extinguishing Trees
verified: true
- type: extinguishing_trees_reward
value: 0.8382346628699452 +/- 0.9897880220029962
name: Extinguishing Trees Reward
verified: true
- type: preparing_trees
value: 295.1830795288086 +/- 11.336644749563497
name: Preparing Trees
verified: true
- type: preparing_trees_reward
value: 295.1830795288086 +/- 11.336644749563497
name: Preparing Trees Reward
verified: true
- type: water_drop
value: 0.9843656837940216 +/- 0.008887930230304724
name: Water Drop
verified: true
- type: water_pickup
value: 0.0007015933631919324 +/- 0.001493842309054032
name: Water Pickup
verified: true
- type: cumulative_reward
value: 294.59887542724607 +/- 11.330578758684899
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 7 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 7
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment