no code implementations • ACL (NL4XAI, INLG) 2020 • Silvia Tulli, Sebastian Wallkötter, Ana Paiva, Francisco S. Melo, Mohamed Chetouani
AI has become prominent in a growing number of systems, and, as a direct consequence, the desire for explainability in such systems has become prominent as well.
1 code implementation • 23 Feb 2024 • Bernardo Esteves, Miguel Vasco, Francisco S. Melo
To address this gap, we propose NeuralThink, a new recurrent architecture that can consistently extrapolate to both symmetrical and asymmetrical tasks, where the dimensionality of the input and output are different.
1 code implementation • 30 Sep 2023 • João G. Ribeiroa, Cassandro Martinhoa, Alberto Sardinhaa, Francisco S. Melo
This paper introduces a formal definition of the setting of ad hoc teamwork under partial observability and proposes a first-principled model-based approach which relies only on prior knowledge and partial observations of the environment in order to perform ad hoc teamwork.
no code implementations • 28 Sep 2023 • Diogo S. Carvalho, Pedro A. Santos, Francisco S. Melo
By exploring the properties of this operator, we identify conditions under which the projected multi-Bellman operator becomes contractive, providing improved fixed-point guarantees compared to the Bellman operator.
1 code implementation • 16 Sep 2023 • Rustam Zayanov, Francisco S. Melo, Manuel Lopes
In particular, we focus on the situation when the teacher has no access to the learner's model and policy, and the feedback from the learner is limited to trajectories that start from states selected by the teacher.
1 code implementation • 10 Jan 2023 • Gonçalo Querido, Alberto Sardinha, Francisco S. Melo
We investigate whether a model with these characteristics is capable of achieving similar performance to state-of-the-art model-free RL agents that access the full input observation.
1 code implementation • 12 Oct 2022 • Pedro P. Santos, Diogo S. Carvalho, Miguel Vasco, Alberto Sardinha, Pedro A. Santos, Ana Paiva, Francisco S. Melo
We introduce hybrid execution in multi-agent reinforcement learning (MARL), a new paradigm in which agents aim to successfully complete cooperative tasks with arbitrary communication levels at execution time by taking advantage of information-sharing among the agents.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 19 Sep 2022 • Miguel Faria, Francisco S. Melo, Ana Paiva
In this paper we investigate the notion of legibility in sequential decision tasks under uncertainty.
1 code implementation • 7 Feb 2022 • Petra Poklukar, Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva, Danica Kragic
Learning representations of multimodal data that are both informative and robust to missing modalities at test time remains a challenging problem due to the inherent heterogeneity of data obtained from different channels.
no code implementations • 30 Jan 2022 • Ramona Merhej, Fernando P. Santos, Francisco S. Melo, Mohamed Chetouani, Francisco C. Santos
In this paper we investigate the consequences of risk diversity in groups of agents learning to play CRDs.
no code implementations • 10 Jan 2022 • João G. Ribeiro, Cassandro Martinho, Alberto Sardinha, Francisco S. Melo
In this paper, we present a novel Bayesian online prediction algorithm for the problem setting of ad hoc teamwork under partial observability (ATPO), which enables on-the-fly collaboration with unknown teammates performing an unknown task without needing a pre-coordination protocol.
1 code implementation • 23 Nov 2021 • Pedro P. Santos, Diogo S. Carvalho, Alberto Sardinha, Francisco S. Melo
We provide a unified theoretical and empirical analysis as to how different properties of the data distribution influence the performance of Q-learning-based algorithms.
1 code implementation • 7 Oct 2021 • Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva
This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions.
no code implementations • 29 Jun 2021 • Ricardo Quinteiro, Francisco S. Melo, Pedro A. Santos
This paper addresses the problem of optimal control using search trees.
no code implementations • 24 Jan 2021 • Guilherme S. Varela, Pedro P. Santos, Alberto Sardinha, Francisco S. Melo
Our methodology addresses the lack of standardization in the literature that renders the comparison of approaches in different works meaningless, due to differences in metrics, environments, and even experimental design and methodology.
no code implementations • NeurIPS 2020 • Diogo Carvalho, Francisco S. Melo, Pedro Santos
In this work, we identify a novel set of conditions that ensure convergence with probability 1 of Q-learning with linear function approximation, by proposing a two time-scale variation thereof.
no code implementations • 17 Oct 2020 • Ana Salta, Rui Prada, Francisco S. Melo
In this document, we present the Geometry Friends Game AI Competition.
no code implementations • 4 Jun 2020 • Miguel Vasco, Francisco S. Melo, Ana Paiva
Humans are able to create rich representations of their external reality.
1 code implementation • 28 Nov 2019 • Rui Silva, Miguel Vasco, Francisco S. Melo, Ana Paiva, Manuela Veloso
In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities.
1 code implementation • 22 Sep 2019 • João Ribeiro, Francisco S. Melo, João Dias
The first hypothesis is driven by the question of whether a deep reinforcement learning algorithm, trained on two similar tasks, is able to outperform two single-task, individually trained algorithms, by more efficiently learning a new, similar task, that none of the three algorithms has encountered before.
no code implementations • 6 Mar 2019 • Miguel Vasco, Francisco S. Melo, David Martins de Matos, Ana Paiva, Tetsunari Inamura
In this work we present \textit{motion concepts}, a novel multimodal representation of human actions in a household environment.