metadata
library_name: hivex
original_train_name: DroneBasedReforestation_difficulty_5_task_2_run_id_2_train
tags:
- hivex
- hivex-drone-based-reforestation
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-DBR-PPO-baseline-task-2-difficulty-5
results:
- task:
type: sub-task
name: pick_up_seed_at_base
task-id: 2
difficulty-id: 5
dataset:
name: hivex-drone-based-reforestation
type: hivex-drone-based-reforestation
metrics:
- type: out_of_energy_count
value: 0.5702619183063508 +/- 0.07710102619282291
name: Out of Energy Count
verified: true
- type: recharge_energy_count
value: 164.77283651448786 +/- 105.66051729333431
name: Recharge Energy Count
verified: true
- type: cumulative_reward
value: 14.895887972116471 +/- 7.701409987004873
name: Cumulative Reward
verified: true
This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 2 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 2
Difficulty: 5
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000
Train & Test Scripts
Download the Environment