We present Pure-Past Action Masking (PPAM), a lightweight approach to action masking for safe reinforcement learning. In PPAM, actions are disallowed (“masked”) according to specifications expressed in Pure-Past Linear Temporal Logic (PPLTL). PPAM can enforce non-Markovian constraints, i.e.,...
04b Atto di convegno in volume
-
-
microRNAs play an important role in post-transcriptional gene regulation. Recently, viral microRNAs have been discovered in several viruses, including Hepatitis B virus. This brief work explores bioinformatics tools for viral/host miRNA research and provides insights into the roles of miRNAs in HBV...
-
Drug repurposing, also known as drug repositioning, is the process of identifying novel therapeutic indications for existing drugs, offering a cost-effective and time-efficient strategy to drug discovery. In this context, we developed a network-based algorithm, named SAveRUNNER (Searching off-lAbel...
-
Neuroblastoma is a disease of disordered development accounting for 15% of childhood cancer deaths. The "cold"immunophenotype frequently occurring of these tumors is likely to contribute to its aggressiveness and refractoriness to treatments, including immune checkpoint blockade, observed in high...
-
Despite the drug approval process consists of extremely rigorous clinical and preclinical studies, not all side effects are identified before its marketing, posing a significant risk to public health. Furthermore, considering the huge use of economic and human resources, in-silico predictive...
-
Sequential Recommender Systems (SRSs) are widely employed to model user behavior over time. However, their robustness in the face of perturbations in training data remains a largely understudied yet critical issue. A fundamental challenge emerges in previous studies aimed at assessing the...
-
The paper presents the training of a surrogate model to mimic the functioning of a text mining social profiling method, emotional Text Mining, applied on the Italian tweets containing #Covid-19 during the first lockdown. This surrogate model is based on stateof-the-art Deep learning models in the...
-
We address the time-optimal, rest-to-rest motion problem under bounded control for a two-mass system interconnected by a visco-elastic joint. A complete geometric solution has recently been found in [1] for the purely elastic case, exploiting symmetries that are lost with the introduction of...
-
Query answering for Knowledge Bases (KBs) amounts to extracting information from the various models of a KB, and presenting the user with an object that represents such information. In the vast majority of cases, this object consists of those tuples of constants that satisfy the query expression...
-
Italian Arthroplasty Registry (Registro Italiano ArtroProtesi, RIAP) is organized as a federation of regional registries, involved on voluntary basis, with the purpose of collecting data to monitor joint prostheses safety and quickly recall patients in case of adverse events. Data collection flows...