Search Results for author: Felipe Meneguzzi

Found 23 papers, 6 papers with code

Online Goal Recognition in Discrete and Continuous Domains Using a Vectorial Representation

no code implementations15 Jul 2023 Douglas Tesch, Leonardo Rosa Amado, Felipe Meneguzzi

While recent work on online goal recognition efficiently infers goals under low observability, comparatively less work focuses on online goal recognition that works in both discrete and continuous domains.

Trajectory Planning

Temporally Extended Goal Recognition in Fully Observable Non-Deterministic Domain Models

no code implementations14 Jun 2023 Ramon Fraga Pereira, Francesco Fuggitti, Felipe Meneguzzi, Giuseppe De Giacomo

We develop the first approach capable of recognizing goals in such settings and evaluate it using different LTLf and PLTLf goals over six FOND planning domain models.

Self-Supervised Adversarial Imitation Learning

2 code implementations21 Apr 2023 Juarez Monteiro, Nathan Gavenski, Felipe Meneguzzi, Rodrigo C. Barros

We address this limitation by incorporating a discriminator into the original framework, offering two key advantages and directly solving a learning problem previous work had.

Behavioural cloning

HyperTensioN and Total-order Forward Decomposition optimizations

no code implementations1 Jul 2022 Maurício Cecílio Magnaguagno, Felipe Meneguzzi, Lavindra de Silva

Hierarchical Task Networks (HTN) planners generate plans using a decomposition process with extra domain knowledge to guide search towards a planning task.

Goal Recognition as Reinforcement Learning

1 code implementation13 Feb 2022 Leonardo Rosa Amado, Reuth Mirsky, Felipe Meneguzzi

In this paper, we develop a framework that combines model-free reinforcement learning and goal recognition to alleviate the need for careful, manual domain design, and the need for costly online executions.

Q-Learning reinforcement-learning +1

Detecting Logical Relation In Contract Clauses

no code implementations2 Nov 2021 Alexandre Yukio Ichida, Felipe Meneguzzi

Contracts underlie most modern commercial transactions defining define the duties and obligations of the related parties in an agreement.

Natural Language Inference Relation

CP-MDP: A CANDECOMP-PARAFAC Decomposition Approach to Solve a Markov Decision Process Multidimensional Problem

1 code implementation27 Feb 2021 Daniela Kuinchtner, Afonso Sales, Felipe Meneguzzi

Markov Decision Process (MDP) is the underlying model for optimal planning for decision-theoretic agents in stochastic environments.

Tensor Decomposition

Inferring Agents Preferences as Priors for Probabilistic Goal Recognition

no code implementations23 Feb 2021 Kin Max Gusmão, Ramon Fraga Pereira, Felipe Meneguzzi

Recent approaches to goal recognition have leveraged planning landmarks to achieve high-accuracy with low runtime cost.

Norm Identification through Plan Recognition

no code implementations6 Oct 2020 Nir Oren, Felipe Meneguzzi

Societal rules, as exemplified by norms, aim to provide a degree of behavioural stability to multi-agent societies.

Imitating Unknown Policies via Exploration

2 code implementations13 Aug 2020 Nathan Gavenski, Juarez Monteiro, Roger Granada, Felipe Meneguzzi, Rodrigo C. Barros

Behavioral cloning is an imitation learning technique that teaches an agent how to behave through expert demonstrations.

Behavioural cloning

Automated Database Indexing using Model-free Reinforcement Learning

no code implementations25 Jul 2020 Gabriel Paludo Licks, Felipe Meneguzzi

Configuring databases for efficient querying is a complex task, often carried out by a database administrator.

reinforcement-learning Reinforcement Learning (RL)

Visual Explanation for Identification of the Brain Bases for Dyslexia on fMRI Data

no code implementations17 Jul 2020 Laura Tomaz Da Silva, Nathalia Bianchini Esper, Duncan D. Ruiz, Felipe Meneguzzi, Augusto Buchweitz

However, the success of machine learning classification algorithms on neurofunctional data has been limited to more homogeneous data sets of dozens of participants.

BIG-bench Machine Learning Classification +1

The More the Merrier?! Evaluating the Effect of Landmark Extraction Algorithms on Landmark-Based Goal Recognition

no code implementations6 May 2020 Kin Max Piamolini Gusmão, Ramon Fraga Pereira, Felipe Meneguzzi

Recent approaches to goal and plan recognition using classical planning domains have achieved state of the art results in terms of both recognition time and accuracy by using heuristics based on planning landmarks.

HAPRec: Hybrid Activity and Plan Recognizer

no code implementations28 Apr 2020 Roger Granada, Ramon Fraga Pereira, Juarez Monteiro, Leonardo Amado, Rodrigo C. Barros, Duncan Ruiz, Felipe Meneguzzi

Computer-based assistants have recently attracted much interest due to its applicability to ambient assisted living.

Action Recognition

Augmented Behavioral Cloning from Observation

2 code implementations28 Apr 2020 Juarez Monteiro, Nathan Gavenski, Roger Granada, Felipe Meneguzzi, Rodrigo Barros

Imitation from observation is a computational technique that teaches an agent on how to mimic the behavior of an expert by observing only the sequence of states from the expert demonstrations.

Behavioural cloning

Classifying Norm Conflicts using Learned Semantic Representations

no code implementations13 May 2019 João Paulo Aires, Roger Granada, Juarez Monteiro, Rodrigo C. Barros, Felipe Meneguzzi

While most social norms are informal, they are often formalized by companies in contracts to regulate trades of goods and services.

An LP-Based Approach for Goal Recognition as Planning

no code implementations10 May 2019 Luísa R. de A. Santos, Felipe Meneguzzi, Ramon Fraga Pereira, André Grahl Pereira

Goal recognition aims to recognize the set of candidate goals that are compatible with the observed behavior of an agent.

Combinatorial Optimization

Using Sub-Optimal Plan Detection to Identify Commitment Abandonment in Discrete Environments

no code implementations26 Apr 2019 Ramon Fraga Pereira, Nir Oren, Felipe Meneguzzi

Assessing whether an agent has abandoned a goal or is actively pursuing it is important when multiple agents are trying to achieve joint goals, or when agents commit to achieving goals for each other.

Landmark-Based Approaches for Goal Recognition as Planning

no code implementations26 Apr 2019 Ramon Fraga Pereira, Nir Oren, Felipe Meneguzzi

The task of recognizing goals and plans from missing and full observations can be done efficiently by using automated planning techniques.

LSTM-Based Goal Recognition in Latent Space

no code implementations15 Aug 2018 Leonardo Amado, João Paulo Aires, Ramon Fraga Pereira, Maurício C. Magnaguagno, Roger Granada, Felipe Meneguzzi

Approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms capable of recognizing goals.

General Classification

Heuristic Approaches for Goal Recognition in Incomplete Domain Models

no code implementations16 Apr 2018 Ramon Fraga Pereira, Felipe Meneguzzi

Recent approaches to goal recognition have progressively relaxed the assumptions about the amount and correctness of domain knowledge and available observations, yielding accurate and efficient algorithms.

Landmark-Based Plan Recognition

1 code implementation5 Apr 2016 Ramon Fraga Pereira, Felipe Meneguzzi

Recognition of goals and plans using incomplete evidence from action execution can be done efficiently by using planning techniques.

Cannot find the paper you are looking for? You can Submit a new open access paper.