Search

Partially Observable Markov Decision Processes (POMDPs) are a powerful framework for planning under uncertainty. They allow to model state uncertainty as a belief probability distribution. Approximate solvers based on Monte Carlo sampling show great success to relax the computational demand and perform online planning. However, scaling to complex realistic domains with many actions and long planning horizons is still a major challenge, and a key point to achieve good performance is guiding the action-selection process with domain-dependent policy heuristics which are tailored for the specific application domain. We propose to learn high-quality heuristics from POMDP traces of executions generated by any solver. We convert the belief-action pairs to a logical semantics, and exploit data- and time-efficient Inductive Logic Programming (ILP) to generate interpretable belief-based policy specifications, which are then used as online heuristics. We evaluate thoroughly our methodology on two notoriously challenging POMDP problems, involving large action spaces and long planning horizons, namely, rocksample and pocman. Considering different state-of-the-art online POMDP solvers, including POMCP, DESPOT and AdaOPS, we show that learned heuristics expressed in Answer Set Programming (ASP) yield performance superior to neural networks and similar to optimal handcrafted taskspecific heuristics within lower computational time. Moreover, they well generalize to more challenging scenarios not experienced in the training phase (e.g., increasing rocks and grid size in rocksample, incrementing the size of the map and the aggressivity of ghosts in pocman). [ABSTRACT FROM AUTHOR]

workflow for data analysis is introduced to synthesize flux regulation maps of a Metabolic P system from time series of data observed in laboratory. The procedure is successfully tested on a significant case study, the photosynthetic phenomenon called NPQ, which determines plant accommodation to environmental light. A previously introduced MP model of such a photosynthetic process has been improved, by providing an MP system with a simpler regulative network that reproduces the observed behaviors of the natural system. Two regression techniques were employed to find out the regulation maps, and interesting experimental results came out in the context of their residual analysis for model validation. [ABSTRACT FROM AUTHOR]