This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 4 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 4
Difficulty: 5
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000
Train & Test Scripts
Download the Environment
Evaluation results
- Highest Potential Soild Found on hivex-drone-based-reforestationself-reported0.9688162982463837 +/- 0.03514935896725512
- Out of Energy Count on hivex-drone-based-reforestationself-reported0.6642222416400909 +/- 0.0670919881726494
- Cumulative Reward on hivex-drone-based-reforestationself-reported-0.02769417219361685 +/- 0.028260583915391758