This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 0 with difficulty 8 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 0
Difficulty: 8
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-reported2.231035829782486 +/- 0.8328265468613688
- Cumulative Distance Until Tree Drop on hivex-drone-based-reforestationself-reported66.65770332336426 +/- 16.760894397204105
- Cumulative Distance to Existing Trees on hivex-drone-based-reforestationself-reported61.44380241394043 +/- 13.630261327963224
- Cumulative Normalized Distance Until Tree Drop on hivex-drone-based-reforestationself-reported0.22310358494520188 +/- 0.08328265504237621
- Cumulative Tree Drop Reward on hivex-drone-based-reforestationself-reported5.744872629642487 +/- 1.9187415652465019
- Out of Energy Count on hivex-drone-based-reforestationself-reported0.9406349241733551 +/- 0.06549559550080679
- Recharge Energy Count on hivex-drone-based-reforestationself-reported10.602158679962159 +/- 1.2842570609336479
- Tree Drop Count on hivex-drone-based-reforestationself-reported1.0329841363430023 +/- 0.06435620343022462
- Cumulative Reward on hivex-drone-based-reforestationself-reported8.81026906967163 +/- 3.1991946865922416