This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 0 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 0
Difficulty: 2
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000
Train & Test Scripts
Download the Environment
Evaluation results
- Cumulative Distance Reward on hivex-drone-based-reforestationself-reported2.830362557172775 +/- 0.8731884646965687
- Cumulative Distance Until Tree Drop on hivex-drone-based-reforestationself-reported81.5349309539795 +/- 16.35440671615
- Cumulative Distance to Existing Trees on hivex-drone-based-reforestationself-reported51.15435367584229 +/- 11.396382191072137
- Cumulative Normalized Distance Until Tree Drop on hivex-drone-based-reforestationself-reported0.28303625583648684 +/- 0.0873188485354732
- Cumulative Tree Drop Reward on hivex-drone-based-reforestationself-reported6.897729444503784 +/- 1.9902223153268046
- Out of Energy Count on hivex-drone-based-reforestationself-reported0.9944761908054351 +/- 0.023806801146583904
- Recharge Energy Count on hivex-drone-based-reforestationself-reported9.503872995376588 +/- 0.6012074882399382
- Tree Drop Count on hivex-drone-based-reforestationself-reported0.9864761888980865 +/- 0.03546595715538237
- Cumulative Reward on hivex-drone-based-reforestationself-reported9.817112922668457 +/- 2.8792400845989854