Zobrazeno 1 - 10
of 831
pro vyhledávání: '"A, Poiani"'
We study the fixed-confidence best-arm identification problem in unimodal bandits, in which the means of the arms increase with the index of the arm up to their maximum, then decrease. We derive two lower bounds on the stopping time of any algorithm.
Externí odkaz:
http://arxiv.org/abs/2411.01898
Policy evaluation via Monte Carlo (MC) simulation is at the core of many MC Reinforcement Learning (RL) algorithms (e.g., policy gradient methods). In this context, the designer of the learning system specifies an interaction budget that the agent us
Externí odkaz:
http://arxiv.org/abs/2410.13463
Autor:
Poiani, Riccardo, Degenne, Rémy, Kaufmann, Emilie, Metelli, Alberto Maria, Restelli, Marcello
In bandit best-arm identification, an algorithm is tasked with finding the arm with highest mean reward with a specified accuracy as fast as possible. We study multi-fidelity best-arm identification, in which the algorithm can choose to sample an arm
Externí odkaz:
http://arxiv.org/abs/2406.03033
Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of interest, however,
Externí odkaz:
http://arxiv.org/abs/2401.03857
Stochastic multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a stochastic reward. Within the context of best-arm identification (BAI) problems, the goal of the age
Externí odkaz:
http://arxiv.org/abs/2308.15552
In Reinforcement Learning (RL), an agent acts in an unknown environment to maximize the expected cumulative discounted sum of an external reward signal, i.e., the expected return. In practice, in many tasks of interest, such as policy optimization, t
Externí odkaz:
http://arxiv.org/abs/2305.04361
Autor:
Poiani, Sarah, Vassilev, Janet
Expanding on the work of Kemp, Ratliff and Shah, for any closure ${\rm cl}$ defined on a class of modules over a Noetherian ring, we develop the theory of ${\rm cl}$-prereductions of submodules. For any interior ${\rm i}$ on a class of $R$-modules, w
Externí odkaz:
http://arxiv.org/abs/2303.00144
With the continuous growth of the global economy and markets, resource imbalance has risen to be one of the central issues in real logistic scenarios. In marine transportation, this trade imbalance leads to Empty Container Repositioning (ECR) problem
Externí odkaz:
http://arxiv.org/abs/2207.12509
Autor:
Tatiane Poiani Mango, Márcia Helena Archilha Rani, Maria Goretti Alves Moreira, Lilian Cláudia Ulian Junqueira, Janaína Luiza dos Santos
Publikováno v:
Prometeica, Vol 30 (2024)
Atualmente, com o aumento da longevidade, uma discussão sobre a qualidade de vida e saúde mental dos idosos se faz importante e, mais do que isso, lança luz para a compreensão das resoluções que a sociedade revela ao tópico da longevidade, com
Externí odkaz:
https://doaj.org/article/726a3f2c0d274648ba845cc7e4c45d7c
Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to related tasks. H
Externí odkaz:
http://arxiv.org/abs/2105.08834