philippds's picture
Upload 15 files
28899cc verified
metadata
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_4_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-4
    results:
      - task:
          type: sub-task
          name: pick_up_water
          task-id: 5
          difficulty-id: 4
        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: 94.79416007995606 +/- 0.3539865655275776
            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 4 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Aerial Wildfire Suppression
Task: 5
Difficulty: 4
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000

Train & Test Scripts
Download the Environment