philippds's picture
Upload README.md
2349ef2 verified
metadata
library_name: hivex
original_train_name: DroneBasedReforestation_difficulty_1_task_0_run_id_2_train
tags:
  - hivex
  - hivex-drone-based-reforestation
  - reinforcement-learning
  - multi-agent-reinforcement-learning
model-index:
  - name: hivex-DBR-PPO-baseline-task-0-difficulty-1
    results:
      - task:
          type: main-task
          name: main_task
          task-id: 0
          difficulty-id: 1
        dataset:
          name: hivex-drone-based-reforestation
          type: hivex-drone-based-reforestation
        metrics:
          - type: cumulative_distance_reward
            value: 2.0864201402664184 +/- 0.6296944874797746
            name: Cumulative Distance Reward
            verified: true
          - type: cumulative_distance_until_tree_drop
            value: 63.19091514587402 +/- 12.303839558575664
            name: Cumulative Distance Until Tree Drop
            verified: true
          - type: cumulative_distance_to_existing_trees
            value: 61.76650863647461 +/- 13.908253887773586
            name: Cumulative Distance to Existing Trees
            verified: true
          - type: cumulative_normalized_distance_until_tree_drop
            value: 0.20864201247692107 +/- 0.06296944883377423
            name: Cumulative Normalized Distance Until Tree Drop
            verified: true
          - type: cumulative_tree_drop_reward
            value: 5.931592869758606 +/- 1.8518746378631161
            name: Cumulative Tree Drop Reward
            verified: true
          - type: out_of_energy_count
            value: 0.9266984140872956 +/- 0.06184757754397895
            name: Out of Energy Count
            verified: true
          - type: recharge_energy_count
            value: 10.601777839660645 +/- 1.2478378815502142
            name: Recharge Energy Count
            verified: true
          - type: tree_drop_count
            value: 1.0418095350265504 +/- 0.08056789785926544
            name: Tree Drop Count
            verified: true
          - type: cumulative_reward
            value: 8.961133165359497 +/- 2.7381643935331064
            name: Cumulative Reward
            verified: true

This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 0 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Drone-Based Reforestation
Task: 0
Difficulty: 1
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000

Train & Test Scripts
Download the Environment