maya-multimodal

Qwen3.5-4B-aerialsim-rl-step100

README

License: apache-2.0

Training

Base: Qwen/Qwen3.5-4B
Env: aerialsim-env with 17 scenario families, Cosys-AirSim / UE5.5 Blocks scene, obs_mode="both" (image + text state), binary reward
GRPO, batch=8, group=4, lr=5e-7, T=0.3 train / 0.0 eval, seq_len=8192
100 training steps

Per-family eval (T=0, n=8 per family, deterministic single decode)

15/17 families perfect. patrol_with_reroute also 8/8 (RL closes the last 2 fails from cold-4B's 6/8). Only multi_obstacle_dense remains at 3/8 due to oracle noise (heuristic policy scores 5/8 on the same family).

Aggregate: 131/136 = 0.963 (matches the heuristic policy ceiling).