ELENA UMILI

Dottoressa di ricerca

ciclo: XXXV


supervisore: Professor De Giacomo

Titolo della tesi: Discovering logical knowledge in non-symbolic domains

Deep learning and symbolic artificial intelligence remain the two main paradigms in Artificial Intelligence (AI), each presenting their own strengths and weaknesses. Artificial agents should integrate both of these aspects of AI in order to show general intelligence and solve complex problems in real-world scenarios; similarly to how humans use both the analytical left side and the intuitive right side of their brain in their lives. However, one of the main obstacles hindering this integration is the Symbol Grounding Problem \cite{symbol_grounding_problem}, which is the capacity to map physical world observations to a set of symbols. In this thesis, we combine symbolic reasoning and deep learning in order to better represent and reason with abstract knowledge. In particular, we focus on solving non-symbolic-state Reinforcement Learning environments using a symbolic logical domain. We consider different configurations: (i) unknown knowledge of both the symbol grounding function and the symbolic logical domain, (ii) unknown knowledge of the symbol grounding function and prior knowledge of the domain, (iii) imperfect knowledge of the symbols grounding function and unknown knowledge of the domain. We develop algorithms and neural network architectures that are general enough to be applied to different kinds of environments, which we test on both continuous-state control problems and image-based environments. Specifically, we develop two kinds of architectures: one for Markovian RL tasks and one for non-Markovian RL domains. The first is based on model-based RL and representation learning, and is inspired by the substantial prior work in state abstraction for RL \cite{Li06towardsa}. The second is mainly based on recurrent neural networks and continuous relaxations of temporal logic domains. In particular, the first approach extracts a symbolic STRIPS-like abstraction for control problems. For the second approach, we explore connections between recurrent neural networks and finite state machines, and we define \textit{Visual Reward Machines}, an extension to non-symbolic domains of Reward Machines \cite{reward-machine-sheila}, which are a popular approach to non-Markovian RL tasks.

Produzione scientifica

11573/1688958 - 2023 - Neurosymbolic Integration of Linear Temporal Logic in Non Symbolic Domains
Umili, Elena - 04b Atto di convegno in volume
congresso: 20th European Conference of Multi-Agents Systems (EUMAS 2023) (Naples, Italy)
libro: Multi-Agent Systems - 20th European Conference, {EUMAS} 2023, Naples, Italy, September 14-15, 2023, Proceedings - ()

11573/1684340 - 2023 - Visual reward machines
Umili, Elena; Argenziano, Francesco; Barbin, Aymeric; Capobianco, Roberto - 04b Atto di convegno in volume
congresso: 17th International Workshop on Neural-Symbolic Learning and Reasoning (La Certosa di Pontignano; Italy)
libro: Neural-Symbolic Learning and Reasoning 2022 - ()

11573/1688956 - 2023 - Grounding LTLf Specifications in Image Sequences
Umili, Elena; Capobianco, Roberto; De Giacomo, Giuseppe - 04h Atto di convegno in rivista scientifica o di classe A
rivista: Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning (Pierre Marquis, Tran Cao Son, Gabriele Kern-Isberner) pp. - - issn: - wos: (0) - scopus: 2-s2.0-85176812706 (0)
congresso: 20th International Conference on Principles of Knowledge Representation and Reasoning (KR 2023) (Rhodes, Greece)

11573/1657086 - 2022 - Grounding LTLf specifications in images
Umili, Elena; Capobianco, Roberto; De Giacomo, Giuseppe - 04b Atto di convegno in volume
congresso: 16th International Workshop on Neural-Symbolic Learning and Reasoning (Cumberland Lodge, Windsor Great Park, United Kingdom)
libro: Proceedings of the 16th International Workshop on Neural-Symbolic Learning and Reasoning - ()

11573/1581213 - 2021 - Learning a Symbolic Planning Domain through the Interaction with Continuous Environments
Umili, Elena; Antonioni, Emanuele; Riccio, Francesco; Capobianco, Roberto; Nardi, Daniele; De Giacomo, Giuseppe - 04f Poster
congresso: The International Conference on Automated Planning, ICAPS 2021 (Guangzhou, China)
libro: Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL), workshop at ICAPS 2021 - ()

11573/1438177 - 2020 - Communication-based and Communication-less approaches for Robust Cooperative Planning in Construction with a Team of UAVs
Umili, Elena; Tognon, Marco; Sanalitro, Dario; Oriolo, Giuseppe; Franchi, Antonio - 04b Atto di convegno in volume
congresso: 2020 International Conference on Unmanned Aircraft Systems (ICUAS) (Athens; Greece)
libro: Proceedings of the International Conference on Unmanned Aircraft Systems (ICUAS), 2020 - ()

¬© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma