Zobrazeno 1 - 10
of 1 988
pro vyhledávání: '"Melo, A. S."'
The general-utility Markov decision processes (GUMDPs) framework generalizes the MDPs framework by considering objective functions that depend on the frequency of visitation of state-action pairs induced by a given policy. In this work, we contribute
Externí odkaz:
http://arxiv.org/abs/2409.15128
We contribute NeuralSolver, a novel recurrent solver that can efficiently and consistently extrapolate, i.e., learn algorithms from smaller problems (in terms of observation size) and execute those algorithms in large problems. Contrary to previous r
Externí odkaz:
http://arxiv.org/abs/2402.15393
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
Externí odkaz:
http://arxiv.org/abs/2310.01439
We study the convergence of $Q$-learning with linear function approximation. Our key contribution is the introduction of a novel multi-Bellman operator that extends the traditional Bellman operator. By exploring the properties of this operator, we id
Externí odkaz:
http://arxiv.org/abs/2309.16819
We study the problem of teaching via demonstrations in sequential decision-making tasks. 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 trajec
Externí odkaz:
http://arxiv.org/abs/2309.09095
This work proposes a novel model-free Reinforcement Learning (RL) agent that is able to learn how to complete an unknown task having access to only a part of the input observation. We take inspiration from the concepts of visual attention and active
Externí odkaz:
http://arxiv.org/abs/2301.03730
Autor:
Iohanathana, Jonathas F. O.1 jonathas.oliveira@ifce.edu.br, Melo, Guilherme S. S. A.2 melog@unb.br
Publikováno v:
Latin American Journal of Solids & Structures. 2024, Vol. 21 Issue 9, p1-20. 20p.
Autor:
Melo, Renato S.1,2 (AUTHOR) renatomelo10@hotmail.com
Publikováno v:
Journal of Audiology & Otology. Oct2024, Vol. 28 Issue 4, p314-317. 4p.
Autor:
Santos, Pedro P., Carvalho, Diogo S., Vasco, Miguel, Sardinha, Alberto, Santos, Pedro A., Paiva, Ana, Melo, Francisco S.
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
Externí odkaz:
http://arxiv.org/abs/2210.06274
In this paper we investigate the notion of legibility in sequential decision tasks under uncertainty. Previous works that extend legibility to scenarios beyond robot motion either focus on deterministic settings or are computationally too expensive.
Externí odkaz:
http://arxiv.org/abs/2209.09141