Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 22
Encontrada(s) 1 página(s)

e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Publication Contribución de congreso (ConferenceOutput)

Eliminating Redundant Actions from Plans Using Classical Planning

  • Salerno, Mauricio Federico
  • Fuentetaja Pizán, Raquel
  • Seipp, Jendrik
Even though automated planning is PSPACE-complete in general, satisfcing planners are able to solve large planning tasks quickly. However, the found plans are often far from optimal and may even contain actions that can be removed while maintaining a valid plan. The problem of fnding and eliminating the most expensive set of such redundant actions in a plan is NP-complete and there is a compilation to MaxSAT that solves it. Here, we introduce a simple and natural formulation of the problem as a planning task. Solving it with an optimal planner guarantees fnding a minimal reduction. Our experiments show that this is competitive with the previous state of the art for optimal action elimination.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Generalized planning as heuristic search

  • Segovia-Aguas, Javier
  • Jiménez, Sergio
  • Jonsson, Anders, 1973-
Comunicació presentada a ICAPS2021, celebrat del 2 a 13 d'agost de 2021 de manera virtual., Although heuristic search is one of the most successful approaches to classical planning, this planning paradigm does not apply straightforwardly to Generalized Planning (GP). Planning as heuristic search traditionally addresses the computation of sequential plans by searching in a grounded state-space. On the other hand, GP aims at computing algorithm-like plans that can branch and loop, and that generalize to a (possibly infinite) set of planning instances. This paper adapts the {\em planning as heuristic search} paradigm to the particularities of GP and presents the first native heuristic search approach to GP. First, the paper defines a novel GP solution space that is independent of the number of planning instances in a GP problem, and the size of these instances. Second, the paper defines several evaluation and heuristic functions, that do not require grounding, for guiding a combinatorial search in the GP solution space, making it possible to handle state variables with large numerical domains (e.g. integers). Lastly, the paper defines an algorithm for GP called Best-First Generalized Planning (BFGP), that implements a best-first search in the solution space guided by our evaluation/heuristic functions., Javier Segovia-Aguas is supported by TAILOR, a project funded by EU H2020 research and innovation programme no. 952215, an ERC Advanced Grant no. 885107, and grant TIN-2015-67959-P from MINECO, Spain. Sergio Jiménez is supported by the Ramon y Cajal program, RYC-2015-18009, the Spanish MINECO project TIN2017-88476-C2-1-R. Anders Jonsson is partially supported by Spanish grants PID2019-108141GB-I00 and PCIN-2017-082.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Expressing and exploiting the common subgoal structure of classical planning domains using sketches

  • Drexler, Dominik
  • Seipp, Jendrik
  • Geffner, Héctor
Comunicació presentada a 18th International Conference on Principles of Knowledge Representation and Reasoning (KR2021), celebrat del 3 al 12 de novembre de 2021 de manera virtual., Width-based planning methods deal with conjunctive goals by decomposing problems into subproblems of low width. Algorithms like SIW thus fail when the goal is not easily serializable in this way or when some of the subproblems have a high width. In this work, we address these limitations by using a simple but powerful language for expressing finer problem decompositions introduced recently by Bonet and Geffner, called policy sketches. A policy sketch R over a set of Boolean and numerical features is a set of sketch rules that express how the values of these features are supposed to change. Like general policies, policy sketches are domain general, but unlike policies, the changes captured by sketch rules do not need to be achieved in a single step. We show that many planning domains that cannot be solved by SIW are provably solvable in low polynomial time with the SIW_R algorithm, the version of SIW that employs user-provided policy sketches. Policy sketches are thus shown to be a powerful language for expressing domain-specific knowledge in a simple and compact way and a convenient alternative to languages such as HTNs or temporal logics. Furthermore, they make it easy to express general problem decompositions and prove key properties of them like their width and complexity., This work was partially supported by an ERC Advanced Grant (grant agreement no. 885107), by project TAILOR, funded by EU Horizon 2020 (grant agreement no. 952215), and by the Knut and Alice Wallenberg Foundation. Hector Geffner is a Wallenberg Guest Professor at Linkoping University, Sweden. We used compute resources from the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Learning first-order representations for planning from black box states: new results

  • Rodriguez, Ivan D.
  • Bonet, Blai
  • Romero, Javier
  • Geffner, Héctor
Comunicació presentada a 18th International Conference on Principles of Knowledge Representation and Reasoning (KR2021), celebrat del 3 al 12 de novembre de 2021 de manera virtual., Recently Bonet and Geffner have shown that first-order representations for planning domains can be learned from the structure of the state space without any prior knowledge about the action schemas or domain predicates. For this, the learning problem is formulated as the search for a simplest first-order domain description D that along with information about instances I_i (number of objects and initial state) determine state space graphs G(P_i) that match the observed state graphs G_i where P_i = (D, I_i). The search is cast and solved approximately by means of a SAT solver that is called over a large family of propositional theories that differ just in the parameters encoding the possible number of action schemas and domain predicates, their arities, and the number of objects. In this work, we push the limits of these learners by moving to an answer set programming (ASP) encoding using the CLINGO system. The new encodings are more transparent and concise, extending the range of possible models while facilitating their exploration. We show that the domains introduced by Bonet and Geffner can be solved more efficiently in the new approach, often optimally, and furthermore, that the approach can be easily extended to handle partial information about the state graphs as well as noise that prevents some states from being distinguished., The work is partially supported by an ERC Advanced Grant (No 885107), by project TAILOR, funded by an EU Horizon 2020 Grant (No 952215), and by the Knut and Alice Wallenberg (KAW) Foundation under the WASP program.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

State representation learning for goal-conditioned reinforcement learning

  • Steccanella, Lorenzo
  • Jonsson, Anders, 1973-
Comunicació presentada a European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2022), celebrat del 19 al 23 de setembre de 2022 a Grenoble, França., This paper presents a novel state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to the minimum number of actions needed to transition between them. Compared to previous methods, our approach does not require any domain knowledge, learning from offline and unlabeled data. We show how this representation can be leveraged to learn goal-conditioned policies, providing a notion of similarity between states and goals and a useful heuristic distance to guide planning and reinforcement learning algorithms. Finally, we empirically validate our method in classic control domains and multi-goal environments, demonstrating that our method can successfully learn representations in large and/or continuous domains., Anders Jonsson is partially funded by the Spanish grant PID2019-108141GB-I00 and the European project TAILOR (H2020, GA 952215).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

From Simultaneous to Streaming Machine Translation by Leveraging Streaming History

  • Iranzo-Sánchez, Javier
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
[EN] Simultaneous Machine Translation is the task of incrementally translating an input sentence before it is fully available. Currently, simultaneous translation is carried out by translating each sentence independently of the previously translated text. More generally, Streaming MT can be understood as an extension of Simultaneous MT to the incremental translation of a continuous input text stream. In this work, a state-of-the-art simultaneous sentencelevel MT system is extended to the streaming setup by leveraging the streaming history. Extensive empirical results are reported on IWSLT Translation Tasks, showing that leveraging the streaming history leads to significant quality gains. In particular, the proposed system proves to compare favorably to the best performing systems., The research leading to these results has received funding from the European Union¿s Horizon 2020 research and innovation programme under grant agreements no. 761758 (X5Gon) and 952215 (TAILOR), and Erasmus+ Education programme under grant agreement no. 20-226-093604-SCH (EXPERT); the Government of Spain¿s grant RTI2018-094879-B-I00 (Multisub) funded by MCIN/AEI/10.13039/501100011033 & ¿ERDF A way of making Europe¿, and FPU scholarships FPU18/04135; and the Generalitat Valenciana¿s research project Classroom Activity Recognition (ref. PROMETEO/2019/111). The authors gratefully acknowledge the computer resources at Artemisa, funded by the European Union ERDF and Comunitat Valenciana as well as the technical support provided by the Instituto de Física Corpuscular, IFIC (CSIC-UV).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Optimal Teaching Curricula with Compositional Simplicity Priors

  • García-Piqueras, Manuel
  • Hernández-Orallo, José|||0000-0001-9746-7632
[EN] Machine teaching under strong simplicity priors can teach any concept in universal languages. Remarkably, recent experiments suggest that the teaching sets are shorter than the concept description itself. This raises many important questions about the complexity of concepts and their teaching size, especially when concepts are taught incrementally. In this paper we put a bound to these surprising experimental findings and reconnect teaching size and concept complexity: complex concepts do require large teaching sets. Also, we analyse teaching curricula, and find a new interposition phenomenon: the teaching size of a concept can increase because examples are captured by simpler concepts built on previously acquired knowledge. We provide a procedure that not only avoids interposition but builds an optimal curriculum. These results indicate novel curriculum design strategies for humans and machines., This work was funded by the EU (FEDER) and Spanish MINECO under RTI2018-094403-B-C32, G. Valenciana under PROMETEO/2019/098 and EU's Horizon 2020 research and innovation programme under grant 952215 (TAILOR).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

When AI Difficulty is Easy: The Explanatory Power of Predicting IRT Difficulty

  • Martínez-Plumed, Fernando|||0000-0003-2902-6477
  • C. Monserrat|||0000-0003-1790-8085
  • Hernández-Orallo, José|||0000-0001-9746-7632
  • Castellano, David
[EN] One of challenges of artificial intelligence as a whole is robustness. Many issues such as adversarial examples, out of distribution performance, Clever Hans phenomena, and the wider areas of AI evaluation and explainable AI, have to do with the following question: Did the system fail because it is a hard instance or because something else? In this paper we address this question with a generic method for estimating IRT-based instance difficulty for a wide range of AI domains covering several areas, from supervised feature-based clas- sification to automated reasoning. We show how to estimate difficulty systematically using off-the-shelf machine learning regression models. We illustrate the usefulness of this estima- tion for a range of applications., This work has been partially supported by the EU (FEDER) and Spanish MINECO grant RTI2018-094403-B-C32 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe , Generalitat Valenciana under grant PROMETEO/2019/098, EU s Horizon 2020 research and innovation programme under grant agreement No. 952215 (TAILOR), the Future of Life Institute, FLI, under grant RFP2-152, US DARPA HR00112120007 (RECoG-AI), the AI-Watch and HUMAINT projects by DG CONNECT and DG JRC of the European Commission, and INNEST/2021/317 (Project cofunded by the European Union with the Programa Operativo del Fondo Europeo de Desarrollo Regional (FEDER) de la Comunitat Valenciana 2014-2020).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks

  • Iranzo-Sánchez, Javier
  • Pérez-González de Martos, Alejandro
  • Baquero-Arnal, Pau
  • Jorge-Cano, Javier|||0000-0002-9279-6768
  • Giménez Pastor, Adrián
  • Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Juan, Alfons|||0000-0002-9984-4072
[EN] This work describes the participation of the MLLP-VRAIN research group in the two shared tasks of the IWSLT 2022 conference: Simultaneous Speech Translation and Speech-to-Speech Translation. We present our streaming-ready ASR, MT and TTS systems for Speech Translation and Synthesis from English into German. Our submission combines these systems by means of a cascade approach paying special attention to data preparation and decoding for streaming inference., The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreements no. 761758 (X5Gon) and 952215 (TAILOR), and Erasmus+ Education programme under grant agreement no. 20- 226-093604-SCH (EXPERT); the Government of Spain¿s grant RTI2018-094879-B-I00 (Multisub) funded by MCIN/AEI/10.13039/501100011033 & ERDF A way of making Europe, and FPU scholarships FPU18/04135; and the Generalitat Valenciana¿s research project Classroom Activity Recognition (ref. PROMETEO/2019/111).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Distilling the Effects of Language Model Contamination

  • Mehrbakhsh, Behzad|||0000-0001-9017-989X
  • Martínez-Plumed, Fernando|||0000-0003-2902-6477
  • Hernández-Orallo, José|||0000-0001-9746-7632
[EN] The proportion of AI-generated content permeating the well of knowledge is increasing significantly. Large language models (LLMs) contribute to that contamination but they also suffer from it. However, it is yet to be clarified the effect of different sources of error, be it human-generated or LLM-generated. Controlling for the percentage of error, we explore the impact on LLM fine-tuning when errors come from humans, from other language models or are generated randomly using an aleatoric or epistemic source. In this paper, we compare these different types of error for in-distribution and out-of-distribution experimental settings. By analysing the levels of errors and their distribution, we find a nuanced view: while in-distribution human-generated noise seems more benign than the LLM-generated counterpart, in the out-of-distribution case the model-generated noise may not be necessarily worse., We thank the anonymous reviewers for their comments and Dr. Peter Clark for providing us with the extended version of the OpenBookQA dataset. This work was funded by valgrAI, the Future of Life Institute, FLI, under grant RFP2-152, the EU (FEDER) and Spanish grant RTI2018-094403-B-C32 funded by MCIN/AEI/10.13039/501100011033 and by CIPROM/2022/6 funded by Generalitat Valenciana, EU s Horizon 2020 research and innovation programme under grant agreement No. 952215 (TAILOR), and Spanish grant PID2021-122830OB-C42 (SFERA) funded by MCIN/AEI/10.13039/501100011033 and "ERDF A way of making Europe"
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Europarl-ASR: A Large Corpus of Parliamentary Debates for Streaming ASR Benchmarking and Speech Data Filtering/Verbatimization

  • Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Jorge-Cano, Javier|||0000-0002-9279-6768
  • Giménez Pastor, Adrián
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Juan, Alfons|||0000-0002-9984-4072
  • Iranzo-Sánchez, Javier
  • Baquero-Arnal, Pau
  • Roselló, Nahuel
  • Pérez-González de Martos, Alejandro Manuel
[EN] We introduce Europarl-ASR, a large speech and text corpus of parliamentary debates including 1300 hours of transcribed speeches and 70 million tokens of text in English extracted from European Parliament sessions. The training set is labelled with the Parliament¿s non-fully-verbatim official transcripts, time-aligned. As verbatimness is critical for acoustic model training, we also provide automatically noise-filtered and automatically verbatimized transcripts of all speeches based on speech data filtering and verbatimization techniques. Additionally, 18 hours of transcribed speeches were manually verbatimized to build reliable speaker-dependent and speaker-independent development/test sets for streaming ASR benchmarking. The availability of manual non-verbatim and verbatim transcripts for dev/test speeches makes this corpus useful for the assessment of automatic filtering and verbatimization techniques. This paper describes the corpus and its creation, and provides off-line and streaming ASR baselines for both the speaker-dependent and speaker-independent tasks using the three training transcription sets. The corpus is publicly released under an open licence., [CA] "Europarl-ASR: Un extens corpus parlamentari de referència per a reconeixement de la parla i filtratge/literalització de transcripcions": Presentem Europarl-ASR, un extens corpus de veu i text de debats parlamentaris amb 1300 hores d'intervencions transcrites i 70 milions de paraules de text en anglés extrets de sessions del Parlament Europeu. Les transcripcions oficials del Parlament Europeu, no literals, s'han sincronitzat per a tot el conjunt d'entrenament. Com que l'entrenament de models acústics requereix transcripcions com més literals millor, també s'han inclòs transcripcions filtrades i transcripcions literalitzades de totes les intervencions, basades en tècniques de filtratge i literalització automàtics. A més, s'han inclòs 18 hores de transcripcions literals revisades manualment per definir dos conjunts de validació i avaluació de referència per a reconeixement automàtic de la parla en temps real, amb oradors coneguts i amb oradors desconeguts. Pel fet de disposar de transcripcions literals i no literals, aquest corpus és també ideal per a l'anàlisi de tècniques de filtratge i de literalització. En aquest article, es descriu la creació del corpus i es proporcionen mesures de referència de reconeixement automàtic de la parla en temps real i en diferit, amb oradors coneguts i amb oradors desconeguts, usant els tres conjunts de transcripcions d'entrenament. El corpus es fa públic amb una llicència oberta., This work has received funding from the EU's H2020 research and innovation programme under grant agreements 761758 (X5gon) and 952215 (TAILOR); the Government of Spain's research project Multisub (RTI2018-094879-B-I00, MCIU/AEI/FEDER,EU) and FPU scholarships FPU14/03981 and FPU18/04135; the Generalitat Valenciana's research project Classroom Activity Recognition (PROMETEO/2019/111) and predoctoral research scholarship ACIF/2017/055; and the Universitat Politecnica de València's ` PAID-01-17 R&D support programme.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Program slicing with exception handling

  • Galindo, Carlos|||0000-0002-3569-6218
  • Silva, Josep|||0000-0001-5096-0008
  • Pérez-Rubio, Sergio
[EN] Program slicing is a technique for program analysis and transformation with many different applications such as program debugging, program specialization, and parallelization. The system dependence graph (SDG) is the most commonly used data structure for program slicing. In this paper, we show that the presence of exception-handling constructs can make the SDG produce incorrect and sometimes even incomplete slices. We showcase the instances of incorrectness and incompleteness and we propose a framework for correctly handling exception-related instructions, which includes representation of all possible exception throwing and catching mechanisms, and a new kind of control dependence: conditional control dependence; which produces more precise slices in the presence of catch statements., This work is partially supported by the EU (FEDER) and the Spanish MCI/AEI under Grant No.: TIN2016-76843-C4-1-R and PID2019-104735RB-C41, and by the Generalitat Valenciana under grant Prometeo/2019/098 (DeepTrust). Sergio Pérez was partially supported by Universitat Politècnica de València under FPI grant PAID-01-18.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Stream-level Latency Evaluation for Simultaneous Machine Translation

  • Iranzo-Sánchez, Javier
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
[EN] Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and response time, and with this purpose multiple latency measures have been proposed. However, latency evaluations for simultaneous translation are estimated at the sentence level, not taking into account the sequential nature of a streaming scenario. Indeed, these sentence-level latency measures are not well suited for continuous stream translation, resulting in figures that are not coherent with the simultaneous translation policy of the system being assessed. This work proposes a stream-level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task., The research leading to these results has received funding from the European Union's Horizon 2020 research and innovation program under grant agreement no. 761758 (X5Gon) and 952215 (TAILOR) and Erasmus+ Education program under grant agreement no. 20-226-093604-SCH; the Government of Spain's research project Multisub, ref. RTI2018-094879-B-I00 (MCIU/AEI/FEDER,EU) and FPU scholarships FPU18/04135; and the Generalitat Valenciana's research project Classroom Activity Recognition, ref. PROMETEO/2019/111.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Language Task Difficulty Prediction through LLM-Annotated Meta-Features

  • Moros-Daval, Yael
  • Martínez-Plumed, Fernando|||0000-0003-2902-6477
  • Hernández-Orallo, José|||0000-0001-9746-7632
[EN] Assessing the capabilities of large language models (LLMs) is increasingly challenging due to their generality and uneven task performance. Often, we do not know how much of the success or failure on a particular task is due to the `loading¿ of the language elements in the task, such as narrative understanding, or some other intrinsic (non-linguistic) components, such as domain-specific common sense or reasoning capabilities. Understanding what tasks are most loaded on language and determine the predictability of LLMs on these tasks is crucial for improving benchmarks, designing better LLMs, and ensuring their safe deployment. We present an innovative methodology that uses LLMs to annotate linguistic metafeatures , allowing us to predict task difficulty and understand linguistic loadings more accurately than traditional readability scores. Using GPT-4 for automated annotation, we show strong predictability for a variety of tasks and language models (e.g., MMLU with R2 from 0.68 to 0.83), but observe limited predictability for other tasks (e.g., LSAT with R2 of -0.07)., We acknowledge support from: Grant for Master Studies funded by ValgrAI Valencian Graduate School and Research Network for Artificial Intelligence and Generalitat Valenciana; FISCALTICS (I+D+i PID2022-140110OA-I00), granted by MICIU/AEI/10.13039/ 501100011033 and by ERDF, EU; CIPROM/2022/6 (FASSLOW) and IDIFEDER/2021/05 (CLUSTERIA) funded by Generalitat Valenciana; the EC H2020-EU grant agreement No. 952215 (TAILOR); US DARPA HR00112120007 (RECoG-AI) and Spanish grant PID2021-122830OB-C42 (SFERA) funded by MCIN/AEI/10.13039/501100011033 and ERDF.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Data Dependence for Object-Oriented Programs

  • Galindo, Carlos|||0000-0002-3569-6218
  • Silva, Josep|||0000-0001-5096-0008
  • Pérez-Rubio, Sergio
[EN] The System Dependence Graph (SDG) is a program representation used in several static analyses. In particular, it is the basis of program slicing, a technique that extracts the part of the program that may directly or indirectly affect the values computed at a given program point (known as the slicing criterion). Several approaches have enhanced the SDG representation to deal with object-oriented situations like inheritance, polymorphism, or dynamic bindings. Currently, the most advanced approach is the Java System Dependence Graph (JSysDG), which subsumes previous approaches and that is able to represent all those situations. In this paper, we show that even the JSysDG does not produce complete slices in all cases when some object variables are selected as the slicing criterion. To solve this limitation, we first identify the source of the problem: the representation of dependences between partial definitions of objects is insufficient in the JSysDG, leading to a loss of completeness in many cases. Then, we extend the JSysDG with the addition of a specific flow dependence for object type variables called object-flow dependence. This extension provides a more accurate flow representation between object variables and its data members and allows us to obtain complete slices when an object variable is considered as slicing criterion., This work has been partially supported by the EU (FEDER) and the Spanish MCI/AEI under grants TIN2016-76843-C4-1- R and PID2019-104735RB-C41, by the Generalitat Valenciana under grant Prometeo/2019/098 (DeepTrust), and by TAILOR, a project funded by EU Horizon 2020 research and innovation programme under GA No 952215. Sergio Pérez was partially supported by Universitat Politècnica de València under FPI grant PAID-01-18.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Online action recognition

  • Suárez Hernández, Alejandro
  • Segovia-Aguas, Javier
  • Torras, Carme
  • Alenyà, Guillem
Trabajo presentado en 35th AAAI Conference on Artificial Intelligence, celebrada de forma virtual del 2 al 9 de febrero de 2021, Recognition in planning seeks to find agent intentions, goals or activities given a set of observations and a knowledge library (e.g. goal states, plans or domain theories). In this work we introduce the problem of Online Action Recognition. It consists in recognizing, in an open world, the planning action that best explains a partially observable state transition from a knowledge library of first-order STRIPS actions, which is initially empty. We frame this as an optimization problem, and propose two algorithms to address it: Action Unification (AU) and Online Action Recognition through Unification (OARU). The former builds on logic unification and generalizes two input actions using weighted partial MaxSAT. The latter looks for an action within the library that explains an observed transition. If there is such action, it generalizes it making use of AU, building in this way an AU hierarchy. Otherwise, OARU inserts a Trivial Grounded Action (TGA) in the library that explains just that transition. We report results on benchmarks from the International Planning Competition and PDDLGym, where OARU recognizes actions accurately with respect to expert knowledge, and shows real-time performance., The research leading to these results has received funding from the EU H2020 research and innovation programme under grant agreement no.731761, IMAGINE; the Hu- MoUR project TIN2017-90086-R (AEI/FEDER, UE); and AEI through the María de Maeztu Seal of Excellence to IRI (MDM-2016-0656). Javier Segovia-Aguas was also partially supported by TAILOR, a project funded by EU H2020 research and innovation programme no. 952215, an ERC Advanced Grant no. 885107, and grant TIN-2015-67959-P from MINECO, Spain., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Automatic learning of cognitive exercises for socially assistive robotics

  • Suárez Hernández, Alejandro
  • Andriella, Antonio
  • Taranović, Aleksandar
  • Segovia-Aguas, Javier
  • Torras, Carme
  • Alenyà, Guillem
Trabajo presentado en el 30th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), celebrada de forma virtual del 8 al 12 de agosto de 2021, In this paper, we present a learning approach to facilitate the teaching of new board exercises to assistive robotic systems. We formulate the problem as the learning of action models using Boolean predicates, disjunctive preconditions, and existential quantifiers from demonstrations of successful exercise executions. To be able to cope with exercises whose rules depend on a set of features that are initialized at the beginning of each play-out, we introduce the concept of dynamic context. Furthermore, we show how the learnt knowledge can be represented intuitively in a graphical interface that helps the caregiver understand what the system has learnt. As validation, we conducted a user study in which we evaluated whether and to which extent different types of feedback can affect the subjects¿ performance while teaching three types of exercises: (1) sorting numbers; (2) arranging letters; and (3) reproducing shapes sequences in reversed order. The results suggest that textual and graphical feedback are beneficial., A. Andriella, C. Torras and A. Suarez-Hernandez were partially funded ´ by the European Union´s Horizon 2020 under ERC Advanced Grant CLOTHILDE (no. 741930), G. Alenya by the EU H2020 research and ` innovation programme IMAGINE (no. 731761) and J. Segovia-Aguas by the programme TAILOR (no. 952215). The work was partially supported by the Spanish State Research Agency through the Mar´ıa de Maeztu Seal of Excellence to IRI (MDM-2016-0656).
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

State representation learning for goal-conditioned reinforcement learning

  • Steccanella, Lorenzo
  • Jonsson, Anders, 1973-
Comunicació presentada a European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2022), celebrat del 19 al 23 de setembre de 2022 a Grenoble, França., This paper presents a novel state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to the minimum number of actions needed to transition between them. Compared to previous methods, our approach does not require any domain knowledge, learning from offline and unlabeled data. We show how this representation can be leveraged to learn goal-conditioned policies, providing a notion of similarity between states and goals and a useful heuristic distance to guide planning and reinforcement learning algorithms. Finally, we empirically validate our method in classic control domains and multi-goal environments, demonstrating that our method can successfully learn representations in large and/or continuous domains., Anders Jonsson is partially funded by the Spanish grant PID2019-108141GB-I00 and the European project TAILOR (H2020, GA 952215).
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Learning first-order representations for planning from black box states: new results

  • Rodriguez, Ivan D.
  • Bonet, Blai
  • Romero, Javier
  • Geffner, Héctor
Comunicació presentada a 18th International Conference on Principles of Knowledge Representation and Reasoning (KR2021), celebrat del 3 al 12 de novembre de 2021 de manera virtual., Recently Bonet and Geffner have shown that first-order representations for planning domains can be learned from the structure of the state space without any prior knowledge about the action schemas or domain predicates. For this, the learning problem is formulated as the search for a simplest first-order domain description D that along with information about instances I_i (number of objects and initial state) determine state space graphs G(P_i) that match the observed state graphs G_i where P_i = (D, I_i). The search is cast and solved approximately by means of a SAT solver that is called over a large family of propositional theories that differ just in the parameters encoding the possible number of action schemas and domain predicates, their arities, and the number of objects. In this work, we push the limits of these learners by moving to an answer set programming (ASP) encoding using the CLINGO system. The new encodings are more transparent and concise, extending the range of possible models while facilitating their exploration. We show that the domains introduced by Bonet and Geffner can be solved more efficiently in the new approach, often optimally, and furthermore, that the approach can be easily extended to handle partial information about the state graphs as well as noise that prevents some states from being distinguished., The work is partially supported by an ERC Advanced Grant (No 885107), by project TAILOR, funded by an EU Horizon 2020 Grant (No 952215), and by the Knut and Alice Wallenberg (KAW) Foundation under the WASP program.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Generalized planning as heuristic search

  • Segovia-Aguas, Javier
  • Jiménez, Sergio
  • Jonsson, Anders, 1973-
Comunicació presentada a ICAPS2021, celebrat del 2 a 13 d'agost de 2021 de manera virtual., Although heuristic search is one of the most successful approaches to classical planning, this planning paradigm does not apply straightforwardly to Generalized Planning (GP). Planning as heuristic search traditionally addresses the computation of sequential plans by searching in a grounded state-space. On the other hand, GP aims at computing algorithm-like plans that can branch and loop, and that generalize to a (possibly infinite) set of planning instances. This paper adapts the {\em planning as heuristic search} paradigm to the particularities of GP and presents the first native heuristic search approach to GP. First, the paper defines a novel GP solution space that is independent of the number of planning instances in a GP problem, and the size of these instances. Second, the paper defines several evaluation and heuristic functions, that do not require grounding, for guiding a combinatorial search in the GP solution space, making it possible to handle state variables with large numerical domains (e.g. integers). Lastly, the paper defines an algorithm for GP called Best-First Generalized Planning (BFGP), that implements a best-first search in the solution space guided by our evaluation/heuristic functions., Javier Segovia-Aguas is supported by TAILOR, a project funded by EU H2020 research and innovation programme no. 952215, an ERC Advanced Grant no. 885107, and grant TIN-2015-67959-P from MINECO, Spain. Sergio Jiménez is supported by the Ramon y Cajal program, RYC-2015-18009, the Spanish MINECO project TIN2017-88476-C2-1-R. Anders Jonsson is partially supported by Spanish grants PID2019-108141GB-I00 and PCIN-2017-082.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Expressing and exploiting the common subgoal structure of classical planning domains using sketches

  • Drexler, Dominik
  • Seipp, Jendrik
  • Geffner, Héctor
Comunicació presentada a 18th International Conference on Principles of Knowledge Representation and Reasoning (KR2021), celebrat del 3 al 12 de novembre de 2021 de manera virtual., Width-based planning methods deal with conjunctive goals by decomposing problems into subproblems of low width. Algorithms like SIW thus fail when the goal is not easily serializable in this way or when some of the subproblems have a high width. In this work, we address these limitations by using a simple but powerful language for expressing finer problem decompositions introduced recently by Bonet and Geffner, called policy sketches. A policy sketch R over a set of Boolean and numerical features is a set of sketch rules that express how the values of these features are supposed to change. Like general policies, policy sketches are domain general, but unlike policies, the changes captured by sketch rules do not need to be achieved in a single step. We show that many planning domains that cannot be solved by SIW are provably solvable in low polynomial time with the SIW_R algorithm, the version of SIW that employs user-provided policy sketches. Policy sketches are thus shown to be a powerful language for expressing domain-specific knowledge in a simple and compact way and a convenient alternative to languages such as HTNs or temporal logics. Furthermore, they make it easy to express general problem decompositions and prove key properties of them like their width and complexity., This work was partially supported by an ERC Advanced Grant (grant agreement no. 885107), by project TAILOR, funded by EU Horizon 2020 (grant agreement no. 952215), and by the Knut and Alice Wallenberg Foundation. Hector Geffner is a Wallenberg Guest Professor at Linkoping University, Sweden. We used compute resources from the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973.
Docta Complutense
Publication Contribución de congreso (ConferenceOutput)

Equational Unification and Matching, and Symbolic Reachability Analysis in Maude 3.2 (System Description)

  • Durán, Francisco
  • Eker, Steven
  • Escobar, Santiago
  • Martí Oliet, Narciso
  • Meseguer, José
  • Rubio Cuéllar, Rubén Rafael
  • Talcott, Carolyn
Equational unification and matching are fundamental mechanisms in many automated deduction applications. Supporting them efficiently for as wide as possible a class of equational theories, and in a typed manner supporting type hierarchies, benefits many applications; but this is both challenging and nontrivial. We present Maude 3.2’s efficient support of these features as well as of symbolic reachability analysis of infinite-state concurrent systems based on them.