Hierarchical Neuro-Symbolic Decision Transformer

Ali Baheri, Cecilia Alm
Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, PMLR 284:266-284, 2025.

Abstract

We present a hierarchical neuro-symbolic control framework that 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v284-baheri25a, title = {Hierarchical Neuro-Symbolic Decision Transformer}, author = {Baheri, Ali and Alm, Cecilia}, booktitle = {Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning}, pages = {266--284}, year = {2025}, editor = {H. Gilpin, Leilani and Giunchiglia, Eleonora and Hitzler, Pascal and van Krieken, Emile}, volume = {284}, series = {Proceedings of Machine Learning Research}, month = {08--10 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v284/main/assets/baheri25a/baheri25a.pdf}, url = {https://proceedings.mlr.press/v284/baheri25a.html}, abstract = {We present a hierarchical neuro-symbolic control framework that 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.} }
Endnote
%0 Conference Paper %T Hierarchical Neuro-Symbolic Decision Transformer %A Ali Baheri %A Cecilia Alm %B Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Leilani H. Gilpin %E Eleonora Giunchiglia %E Pascal Hitzler %E Emile van Krieken %F pmlr-v284-baheri25a %I PMLR %P 266--284 %U https://proceedings.mlr.press/v284/baheri25a.html %V 284 %X We present a hierarchical neuro-symbolic control framework that 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.
APA
Baheri, A. & Alm, C.. (2025). Hierarchical Neuro-Symbolic Decision Transformer. Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, in Proceedings of Machine Learning Research 284:266-284 Available from https://proceedings.mlr.press/v284/baheri25a.html.

Related Material