This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 0 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 0
Difficulty: 5
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-reported2.7580876886844634 +/- 0.7562888045399391
- Cumulative Distance Until Tree Drop on hivex-drone-based-reforestationself-reported78.29452056884766 +/- 14.296043451183179
- Cumulative Distance to Existing Trees on hivex-drone-based-reforestationself-reported50.473754501342775 +/- 11.98073606874106
- Cumulative Normalized Distance Until Tree Drop on hivex-drone-based-reforestationself-reported0.2758087694644928 +/- 0.07562888371330763
- Cumulative Tree Drop Reward on hivex-drone-based-reforestationself-reported7.088011031150818 +/- 1.7168094182484812
- Out of Energy Count on hivex-drone-based-reforestationself-reported0.9958095240592957 +/- 0.022119619288807686
- Recharge Energy Count on hivex-drone-based-reforestationself-reported9.258539686203003 +/- 0.587428694662249
- Tree Drop Count on hivex-drone-based-reforestationself-reported0.9893650794029236 +/- 0.03160683668166852
- Cumulative Reward on hivex-drone-based-reforestationself-reported10.612933225631714 +/- 2.659049482325796