action-selection

Training-free decision engine for existing MLX models on Apple Silicon. No fine-tuning or extra decision weights. MLX-LM + experimental MLX-VLM action selection and semantic routing. Related: AnyJev.

Opportunistic planning model package for action selection, based on human behavior in everyday activities

Explainable action ranking from historical sequences — a Rust library and CLI, not a contextual bandit or online-learning library.

Measures action selection and abstention on frozen UI states.

Python/PyBullet port of Prescott et al. (2006)'s basal ganglia robot model — an embedded action selection architecture (EASA) running on real Khepera I geometry with realistic contact physics for a foraging task.

Model development, analyses, and evaluation based on the opportunistic planning package.