This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 0 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Drone-Based Reforestation
Task: 0
Difficulty: 6
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000

Train & Test Scripts
Download the Environment

Downloads last month: -; Downloads are not tracked for this model. How to track

Video Preview

Reinforcement Learning

Collection including hivex-research/hivex-DBR-PPO-baseline-task-0-difficulty-6

Drone-Based Reforestation

Collection

70 items • Updated Jan 7

Evaluation results

Cumulative Distance Reward on hivex-drone-based-reforestation
self-reported

2.278297426700592 +/- 0.7970550172943512
Cumulative Distance Until Tree Drop on hivex-drone-based-reforestation
self-reported

71.83662818908691 +/- 16.138112577766993
Cumulative Distance to Existing Trees on hivex-drone-based-reforestation
self-reported

63.50090087890625 +/- 12.724329294351138
Cumulative Normalized Distance Until Tree Drop on hivex-drone-based-reforestation
self-reported

0.22782974272966386 +/- 0.07970550120723825
Cumulative Tree Drop Reward on hivex-drone-based-reforestation
self-reported

6.105163459777832 +/- 2.096869181395617
Out of Energy Count on hivex-drone-based-reforestation
self-reported

0.9176825439929962 +/- 0.07301305856737815
Recharge Energy Count on hivex-drone-based-reforestation
self-reported

10.315396842956543 +/- 1.078328692209581
Tree Drop Count on hivex-drone-based-reforestation
self-reported

1.0677143037319183 +/- 0.07302193295701627
Cumulative Reward on hivex-drone-based-reforestation
self-reported

9.875887503623963 +/- 3.754279000733476

View on Papers With Code