This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 3 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 3
Difficulty: 6
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-reported1.3454772663116454 +/- 0.25212101346663623
- Cumulative Distance Until Tree Drop on hivex-drone-based-reforestationself-reported48.78826332092285 +/- 5.743127534874983
- Cumulative Distance to Existing Trees on hivex-drone-based-reforestationself-reported64.26434959411621 +/- 5.284372460543501
- Cumulative Normalized Distance Until Tree Drop on hivex-drone-based-reforestationself-reported0.1345477257668972 +/- 0.02521210110839935
- Cumulative Tree Drop Reward on hivex-drone-based-reforestationself-reported4.1371043682098385 +/- 0.5887544719292628
- Out of Energy Count on hivex-drone-based-reforestationself-reported0.031587274074554444 +/- 0.021537219176821762
- Recharge Energy Count on hivex-drone-based-reforestationself-reported10.989339809417725 +/- 0.5768743885606192
- Tree Drop Count on hivex-drone-based-reforestationself-reported0.9577047204971314 +/- 0.02966963426330889
- Cumulative Reward on hivex-drone-based-reforestationself-reported102.36149932861328 +/- 3.0284734534759377