metadata
library_name: hivex
original_train_name: DroneBasedReforestation_difficulty_6_task_4_run_id_2_train
tags:
- hivex
- hivex-drone-based-reforestation
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-DBR-PPO-baseline-task-4-difficulty-6
results:
- task:
type: sub-task
name: find_highest_potential_seed_drop_location
task-id: 4
difficulty-id: 6
dataset:
name: hivex-drone-based-reforestation
type: hivex-drone-based-reforestation
metrics:
- type: highest_potential_soild_found
value: 0.973448144197464 +/- 0.03533347847671178
name: Highest Potential Soild Found
verified: true
- type: out_of_energy_count
value: 0.6642222416400909 +/- 0.0670919881726494
name: Out of Energy Count
verified: true
- type: cumulative_reward
value: '-0.023179268517837956 +/- 0.026497002194857084'
name: Cumulative Reward
verified: true
This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 4 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 4
Difficulty: 6
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000
Train & Test Scripts
Download the Environment