metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_9_task_5_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-5-difficulty-9
results:
- task:
type: sub-task
name: pick_up_water
task-id: 5
difficulty-id: 9
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: water_pickup
value: 0.9976190477609634 +/- 0.010647942115332154
name: Water Pickup
verified: true
- type: cumulative_reward
value: 94.99339561462402 +/- 0.2982787930055043
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 5 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 5
Difficulty: 9
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment