Views
No views yet
| 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 |
1{
2 "mcts_tuning": {
3 "best_ucb_c": 1.41,
4 "ucb_0.5": {
5 "mean_reward": 0.1749,
6 "p50_ms": 110.0,
7 "p95_ms": 125.0
8 },
9 "ucb_1.0": {
10 "mean_reward": 0.172,
11 "p50_ms": 109.0,
12 "p95_ms": 125.0
13 },
14 "ucb_1.41": {
15 "mean_reward": 0.145,
16 "p50_ms": 109.0,
17 "p95_ms": 125.0
18 },
19 "ucb_2.0": {
20 "mean_reward": 0.223,
21 "p50_ms": 109.0,
22 "p95_ms": 125.0
23 },
24 "ucb_3.0": {
25 "mean_reward": 0.4133,
26 "p50_ms": 109.0,
27 "p95_ms": 125.0
28 }
29 }
30}