This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 0 with difficulty 3 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 0
Difficulty: 3
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-reported2.2798677325248717 +/- 0.826199092335029
- Cumulative Distance Until Tree Drop on hivex-drone-based-reforestationself-reported71.01197761535644 +/- 15.915402716637344
- Cumulative Distance to Existing Trees on hivex-drone-based-reforestationself-reported62.63453010559082 +/- 13.028011782073118
- Cumulative Normalized Distance Until Tree Drop on hivex-drone-based-reforestationself-reported0.22798677459359168 +/- 0.08261990936252438
- Cumulative Tree Drop Reward on hivex-drone-based-reforestationself-reported6.079879174232483 +/- 1.9570747333814178
- Out of Energy Count on hivex-drone-based-reforestationself-reported0.9128571474552154 +/- 0.0670314456167534
- Recharge Energy Count on hivex-drone-based-reforestationself-reported10.353745937347412 +/- 1.1334994783704704
- Tree Drop Count on hivex-drone-based-reforestationself-reported1.0618095421791076 +/- 0.07039888032455249
- Cumulative Reward on hivex-drone-based-reforestationself-reported9.758727273941041 +/- 3.0183970200236456