Hierarchical Neuro-Symbolic Decision Transformer
This addresses the problem of robust sequential task execution for AI systems, though it appears incremental as it combines existing symbolic and neural approaches.
The paper tackles long-horizon decision-making under uncertainty by coupling a symbolic planner with a transformer-based policy, resulting in a method that consistently surpasses purely symbolic, purely neural, and hierarchical baselines in success and efficiency in stochastic grid-world domains.
We present a hierarchical neuro-symbolic control framework that tightly couples a classical symbolic planner with a transformer-based policy to address long-horizon decision-making under uncertainty. At the high level, the planner assembles an interpretable sequence of operators that guarantees logical coherence with task constraints, while at the low level each operator is rendered as a sub-goal token that conditions a decision transformer to generate fine-grained actions directly from raw observations. This bidirectional interface preserves the combinatorial efficiency and explainability of symbolic reasoning without sacrificing the adaptability of deep sequence models, and it permits a principled analysis that tracks how approximation errors from both planning and execution accumulate across the hierarchy. Empirical studies in stochastic grid-world domains demonstrate that the proposed method consistently surpasses purely symbolic, purely neural and existing hierarchical baselines in both success and efficiency, highlighting its robustness for sequential tasks.