Anonymous Author(s); (2025) Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies. In: El Fallah Seghrouchni, A and Vorobeychik, Y and Das, S and Nowe, A, (eds.) Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025). (pp. pp. 1-10). IFAAMAS (International Foundation for Autonomous Agents and Multiagent Systems): Detroit, Michigan, USA.

Preview

Text 944_Neural_DNF_MT_A_Neuro_symb.pdf - Accepted Version Download (2MB) | Preview

Abstract

Although deep reinforcement learning has been shown to be effective, the model’s black-box nature presents barriers to direct policy interpretation. To address this problem, we propose a neurosymbolic approach called neural DNF-MT for end-to-end policy learning. The di!erentiable nature of the neural DNF-MT model enables the use of deep actor-critic algorithms for training. At the same time, its architecture is designed so that trained models can be directly translated into interpretable policies expressed as standard (bivalent or probabilistic) logic programs. Moreover, additional layers can be included to extract abstract features from complex observations, acting as a form of predicate invention. The logic representations are highly interpretable, and we show how the bivalent representations of deterministic policies can be edited and incorporated back into a neural model, facilitating manual intervention and adaptation of learned policies. We evaluate our approach on a range of tasks requiring learning deterministic or stochastic behaviours from various forms of observations. Our empirical results show that our neural DNF-MT model performs at the level of competing black-box methods whilst providing interpretable policies.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as XMLCSVJSON

Archive Staff Only

View Item