Reinforcement learning has achieved remarkable success in complex decision-making environments, yet its lack of transparency limits its deployment in practice, especially in safety-critical settings. Shapley values from cooperative game theory provide a principled framework for explaining reinforcement learning; however, the computational cost of Shapley explanations is an obstacle to their use. We introduce FastSVERL, a scalable method for explaining reinforcement learning by approximating Shapley values. FastSVERL is designed to handle the unique challenges of reinforcement learning, including temporal dependencies across multi-step trajectories, learning from off-policy data, and adapting to evolving agent behaviours in real time. FastSVERL introduces a practical, scalable approach for principled and rigorous interpretability in reinforcement learning.

Conditionals are generally considered the backbone of human (and AI) reasoning: the "if-then" connection between two propositions is the stepping stone of arguments and a lot of the research effort in formal logic has focused on this kind of connection. A conditional connection satisfies different properties according to the kind of arguments it is used for. The classical material implication is appropriate for modelling the "ifthen" connection as it is used in Mathematics, but the equivalence between the material implication A B and A B is not appropriate for many other contexts.

Furthermore, interaction with such systems has to happen in a very specific and narrow spectrum of interfaces, with limited margin of flexibility and adaptability. BRIEF SUMMARY Harmonic theory provides a mathematical framework to describe the structure, behavior, evolution and emergence of harmonic systems. A harmonic system is context aware, contains elements that manifest characteristics either collaboratively or independently according to system's expression and can interact with its environment. This theory provides a fresh way to analyze emergence and collaboration of "ad-hoc" and complex systems.

Characteristic models are an alternative, model based, representation for Horn expressions. It has been shown that these two representations are incomparable and each has its advantages over the other. It is therefore natural to ask what is the cost of translating, back and forth, between these representations. Interestingly, the same translation questions arise in database theory, where it has applications to the design of relational databases. This paper studies the computational complexity of these problems. Our main result is that the two translation problems are equivalent under polynomial reductions, and that they are equivalent to the corresponding decision problem. Namely, translating is equivalent to deciding whether a given set of models is the set of characteristic models for a given Horn expression. We also relate these problems to the hypergraph transversal problem, a well known problem which is related to other applications in AI and for which no polynomial time algorithm is known. It is shown that in general our translation problems are at least as hard as the hypergraph transversal problem, and in a special case they are equivalent to it.