Reinforcement Learning (RL) provides a principled framework for sequential decision-making in complex environments. However, state-of-the-art Deep Reinforcement Learning (DRL) algorithms typically require large amounts of training data and often fail to generalize beyond small-scale training scenarios, even on standard benchmarks. We propose a neuro-symbolic DRL approach that incorporates background symbolic knowledge to improve both sample efficiency and generalization to more challenging, unseen tasks. Specifically, partial policies learned in simple domain instances, where high performance can be achieved reliably, are transferred as structured priors to accelerate learning in more complex environments, eliminating the need to tune DRL parameters from scratch. Our method represents partial policies as logical rules in the Answer Set Programming (ASP) formalism and performs online reasoning to guide training through two complementary mechanisms: (i) biasing the action distribution during exploration, and (ii) rescaling Q-values during exploitation. This integration of ASP reasoning with DRL enhances interpretability and trustworthiness while accelerating convergence, particularly in sparse-reward settings and tasks with long planning horizons, without introducing significant computational overhead. We empirically evaluate our approach on challenging variants of gridworld environments under both fully and partially observable settings. Results demonstrate consistent performance improvements over a state-of-the-art reward machine baseline.

This paper proposes an integration of temporal logical reasoning and Partially Observable Markov Decision Processes (POMDPs) to achieve interpretable decision-making under uncertainty with macro-actions. Our method leverages a fragment of Linear Temporal Logic (LTL) based on Event Calculus (EC) to generate persistent (i.e., constant) macro-actions, which guide Monte Carlo Tree Search (MCTS)-based POMDP solvers over a time horizon, significantly reducing inference time while ensuring robust performance. Such macro-actions are learnt via Inductive Logic Programming (ILP) from a few traces of execution (belief-action pairs), thus eliminating the need for manually designed heuristics and requiring only the specification of the POMDP transition model. In the Pocman and Rocksample benchmark scenarios, our learned macro-actions demonstrate increased expressiveness and generality when compared to time-independent heuristics, indeed offering substantial computational efficiency improvements.

We present the architecture of Houdini-2.0, a reasoning system that computes the extension of a defeasible deontic theory given as input, the process of computing the consequences of the rules expressed in the theory itself. The decision process is a sceptical, non-monotonic, and it allows us to determine which prescriptive behaviours are in force (obligations, permissions, prohibitions) along with propositional ones. The system is based on pre-existing algorithmic solutions, and it is implemented as an online platform to deploy the results of a computation in several use cases, including those that pertain legal domain.