philippds's picture
Upload 13 files
c40bc74 verified
metadata
library_name: hivex
original_train_name: DroneBasedReforestation_difficulty_10_task_3_run_id_1_train
tags:
  - hivex
  - hivex-drone-based-reforestation
  - reinforcement-learning
  - multi-agent-reinforcement-learning
model-index:
  - name: hivex-DBR-PPO-baseline-task-3-difficulty-10
    results:
      - task:
          type: sub-task
          name: drop_seed
          task-id: 3
          difficulty-id: 10
        dataset:
          name: hivex-drone-based-reforestation
          type: hivex-drone-based-reforestation
        metrics:
          - type: cumulative_distance_reward
            value: 1.3822244083881379 +/- 0.2799904225640544
            name: Cumulative Distance Reward
            verified: true
          - type: cumulative_distance_until_tree_drop
            value: 49.66127479553223 +/- 7.218445332813338
            name: Cumulative Distance Until Tree Drop
            verified: true
          - type: cumulative_distance_to_existing_trees
            value: 65.08539611816406 +/- 5.7159717268853285
            name: Cumulative Distance to Existing Trees
            verified: true
          - type: cumulative_normalized_distance_until_tree_drop
            value: 0.13822243928909303 +/- 0.027999042034590665
            name: Cumulative Normalized Distance Until Tree Drop
            verified: true
          - type: cumulative_tree_drop_reward
            value: 4.014332270622253 +/- 0.740893757159681
            name: Cumulative Tree Drop Reward
            verified: true
          - type: out_of_energy_count
            value: 0.03652440816164017 +/- 0.02224060499692208
            name: Out of Energy Count
            verified: true
          - type: recharge_energy_count
            value: 10.598072090148925 +/- 0.5897619835270185
            name: Recharge Energy Count
            verified: true
          - type: tree_drop_count
            value: 0.9516399455070496 +/- 0.03216850980609787
            name: Tree Drop Count
            verified: true
          - type: cumulative_reward
            value: 101.69934463500977 +/- 3.379470856148503
            name: Cumulative Reward
            verified: true

This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 3 with difficulty 10 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Drone-Based Reforestation
Task: 3
Difficulty: 10
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000

Train & Test Scripts
Download the Environment