| # 🐝 BeeWalker v6 — Training Results |
|
|
| Training results for the BeeWalker bipedal robot, using PPO and LSTM-based reinforcement learning in MuJoCo. |
|
|
| **GitHub:** [ThomasVuNguyen/makeshit](https://github.com/ThomasVuNguyen/makeshit) |
|
|
| ## Training Runs |
|
|
| | Run | Type | Steps | Videos | Checkpoints | |
| |-----|------|-------|--------|-------------| |
| | [lstm_20260209_154855](./lstm_20260209_154855/) | LSTM | 17.9M | 4 | 0 | |
| | [lstm_20260209_004543](./lstm_20260209_004543/) | LSTM | 29.6M | 296 | 59 | |
| | [lstm_20260208_191752](./lstm_20260208_191752/) | LSTM | 9.9M | 99 | 19 | |
| | [lstm_20260208_190415](./lstm_20260208_190415/) | LSTM | 200K | 2 | 0 | |
| | [lstm_20260208_171335](./lstm_20260208_171335/) | LSTM | 1.2M | 12 | 2 | |
| | [lstm_20260207_013141](./lstm_20260207_013141/) | LSTM | 24.9M | 2489 | 49 | |
|
|
| ## Robot |
|
|
| - **Simulation:** MuJoCo (BipedWalker custom env) |
| - **Servos:** 6× MG996R (hip, knee, ankle × 2) |
| - **Controller:** RP2040 (target deployment) |
| - **Algorithm:** RecurrentPPO (LSTM hidden_size=32) |
| |
| ## How to Use |
| |
| ```bash |
| # Upload results to HuggingFace |
| python tools/upload_hf.py --latest |
|
|
| # Upload all runs |
| python tools/upload_hf.py |
| |
| # Upload specific run |
| python tools/upload_hf.py --run lstm_20260207_013141 |
| ``` |
| |
