Downloads · 30 days
0
mousedroid-weights
ianshank/mousedroid-weights
mousedroid-weights is a robotics model from ianshank. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for pytorch.
Trained weights for MouseDroid autonomous navigation system.
Access
Public
Updated Apr 16, 2026
Repo size
283 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt102 MB · 100%
At a glance
- Task
- Robotics
- Library
- pytorch
- Access
- Public
- Created
- Mar 15, 2026
- Updated
- Apr 16, 2026
- SHA
- c14b81bd
Model card
From the Hugging Face model README
ianshank/mousedroid-weights
Trained weights for MouseDroid autonomous navigation system.
Components
| Component | File | Description |
|---|---|---|
| RSSM World Model | rssm/final.pt | Recurrent State-Space Model |
| MCTS Policy Init | mcts/policy_init.npz | Warm-started PolicyMLP |
| BDI Belief | bdi/belief.npz | Belief encoder weights |
| BDI Desire | bdi/desire.npz | Desire encoder weights |
| BDI Intention | bdi/intention.npz | Intention predictor weights |
| BDI Affect | bdi/affect.npz | Affect estimator weights |
| Constitutional RL | policy.npz, value.npz | PPO policy + value networks |
Training
Trained on Jetson Orin Nano (8 GB) using synthetic observation sequences.
Training Metadata
{
"mcts_tuning": {
"best_ucb_c": 1.41,
"ucb_0.5": {
"mean_reward": 0.1749,
"p50_ms": 110.0,
"p95_ms": 125.0
},
"ucb_1.0": {
"mean_reward": 0.172,
"p50_ms": 109.0,
"p95_ms": 125.0
},
"ucb_1.41": {
"mean_reward": 0.145,
"p50_ms": 109.0,
"p95_ms": 125.0
},
"ucb_2.0": {
"mean_reward": 0.223,
"p50_ms": 109.0,
"p95_ms": 125.0
},
"ucb_3.0": {
"mean_reward": 0.4133,
"p50_ms": 109.0,
"p95_ms": 125.0
}
}
}
- Task
- Robotics
- Library
- pytorch
- Created
- Mar 15, 2026
- Updated
- Apr 16, 2026