metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_4_task_7_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-7-difficulty-4
results:
- task:
type: sub-task
name: find_fire
task-id: 7
difficulty-id: 4
dataset:
name: hivex-aerial-wildfire-suppression
type: hivex-aerial-wildfire-suppression
metrics:
- type: crash_count
value: 0.10086543383076788 +/- 0.10339308792925168
name: Crash Count
verified: true
- type: cumulative_reward
value: 74.68694515228272 +/- 39.010904385486974
name: Cumulative Reward
verified: true
This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 7 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 7
Difficulty: 4
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment