This model serves as the baseline for the Drone-Based Reforestation environment, trained and tested on task 6 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Drone-Based Reforestation
Task: 6
Difficulty: 4
Algorithm: PPO
Episode Length: 2000
Training max_steps: 1200000
Testing max_steps: 300000
Train & Test Scripts
Download the Environment
Evaluation results
- Furthest Distance Explored on hivex-drone-based-reforestationself-reported158.60399871826172 +/- 13.606457942958817
- Out of Energy Count on hivex-drone-based-reforestationself-reported0.5861587435007095 +/- 0.07528415521708526
- Recharge Energy Count on hivex-drone-based-reforestationself-reported127.55600050918758 +/- 115.90250626363267
- Cumulative Reward on hivex-drone-based-reforestationself-reported8.652405815720558 +/- 7.325451196047886