Search Results for author: Francisco S. Melo

Found 17 papers, 6 papers with code

Learning from Explanations and Demonstrations: A Pilot Study

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.

Transfer Learning

Learning to Perceive in Deep Model-Free Reinforcement Learning

1 code implementation10 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.

Atari Games Hard Attention +2

Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning

1 code implementation12 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 perform cooperative tasks with any communication level at execution time by taking advantage of information-sharing among the agents.

Multi-agent Reinforcement Learning reinforcement-learning +1

Geometric Multimodal Contrastive Representation Learning

1 code implementation7 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.

reinforcement Learning Representation Learning

Learning Collective Action under Risk Diversity

no code implementations30 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.

Assisting Unknown Teammates in Unknown Tasks: Ad Hoc Teamwork under Partial Observability

no code implementations10 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.

Understanding the Impact of Data Distribution on Q-learning with Function Approximation

no code implementations23 Nov 2021 Pedro P. Santos, Francisco S. Melo, Alberto Sardinha, Diogo S. Carvalho

Second, we provide a novel four-state MDP that highlights the impact of the data distribution in the performance of a Q-learning algorithm with function approximation, both in online and offline settings.


How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents

1 code implementation7 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.

Atari Games reinforcement-learning +1

A Methodology for the Development of RL-Based Adaptive Traffic Signal Controllers

no code implementations24 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.

Experimental Design reinforcement-learning +1

A new convergent variant of Q-learning with linear function approximation

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.

Q-Learning reinforcement Learning

Playing Games in the Dark: An approach for cross-modality transfer in reinforcement learning

1 code implementation28 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.

OpenAI Gym reinforcement-learning +1

Multi-task Learning and Catastrophic Forgetting in Continual Reinforcement Learning

1 code implementation22 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.

Continual Learning Multi-Task Learning +2

Learning multimodal representations for sample-efficient recognition of human actions

no code implementations6 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.

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