---
library_name: hivex
original_train_name: DroneBasedReforestation_difficulty_3_task_3_run_id_2_train
tags:
- hivex
- hivex-drone-based-reforestation
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-DBR-PPO-baseline-task-3-difficulty-3
  results:
  - task:
      type: sub-task
      name: drop_seed
      task-id: 3
      difficulty-id: 3
    dataset:
      name: hivex-drone-based-reforestation
      type: hivex-drone-based-reforestation
    metrics:
    - type: cumulative_distance_reward
      value: 1.3285970211029052 +/- 0.2026441385418575
      name: Cumulative Distance Reward
      verified: true
    - type: cumulative_distance_until_tree_drop
      value: 47.9919889831543 +/- 5.6265548956948175
      name: Cumulative Distance Until Tree Drop
      verified: true
    - type: cumulative_distance_to_existing_trees
      value: 65.33616821289063 +/- 5.588311427115504
      name: Cumulative Distance to Existing Trees
      verified: true
    - type: cumulative_normalized_distance_until_tree_drop
      value: 0.1328597016632557 +/- 0.0202644141787037
      name: Cumulative Normalized Distance Until Tree Drop
      verified: true
    - type: cumulative_tree_drop_reward
      value: 3.886158046722412 +/- 0.6842395486126234
      name: Cumulative Tree Drop Reward
      verified: true
    - type: out_of_energy_count
      value: 0.0312901480961591 +/- 0.022431259975135485
      name: Out of Energy Count
      verified: true
    - type: recharge_energy_count
      value: 10.788163661956787 +/- 0.49577403931861075
      name: Recharge Energy Count
      verified: true
    - type: tree_drop_count
      value: 0.9570524430274964 +/- 0.029623495473389997
      name: Tree Drop Count
      verified: true
    - type: cumulative_reward
      value: 102.01719390869141 +/- 3.2560710700635593
      name: Cumulative Reward
      verified: true
---

This model serves as the baseline for the **Drone-Based Reforestation** environment, trained and tested on task <code>3</code> with difficulty <code>3</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>Environment: **Drone-Based Reforestation**<br>Task: <code>3</code><br>Difficulty: <code>3</code><br>Algorithm: <code>PPO</code><br>Episode Length: <code>2000</code><br>Training <code>max_steps</code>: <code>1200000</code><br>Testing <code>max_steps</code>: <code>300000</code><br><br>Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>Download the [Environment](https://github.com/hivex-research/hivex-environments)