Sergio Pérez

Sergio Pérez

Auto-generated profile, based on publicly available information

Sergio Pérez

Repsol Technology Lab , Repsol , Spain

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2021 in Future Generation Computer Systems
Verified
Journal Article
Open access
SPSergio Pérez
Sergio Pérez
PAPatricia Arroba
Patricia Arroba
JFJosé Manuel Moya Fernández
José Manuel Moya Fernández

1 October 2023 in Journal of Artificial Intelligence and Soft Computing Research
Verified
Journal Article
Open access
PDF file
JPJosé Luis Pérez
José Luis Pérez
Javier Corrochano JiménezJavier Corrochano Jiménez
Javier Corrochano Jiménez
FPFrancisco Javier García Polo
Francisco Javier García Polo
RMRubén Majadas
Rubén Majadas
CICristina Ibañez-Llano
Cristina Ibañez-Llano
FFFernando Fernández
Fernando Fernández
In many Reinforcement Learning (RL) tasks, the classical online interaction of the learning agent with the environment is impractical, either because such interaction is expensive or dangerous. In these cases, previous gathered data can be used, arising what is typically called Offline RL. However, this type of learning faces a large number of challenges, mostly derived from the fact that exploration/exploitation trade-off is overshadowed. In addition, the historical data is usually biased by the way it was obtained, typically, a sub-optimal controller, producing a distributional shift from historical data and the one required to learn the optimal policy. In this paper, we present a novel approach to deal with the uncertainty risen by the absence or sparse presence of some state-action pairs in the learning data. Our approach is based on shaping the reward perceived from the environment to ensure the task is solved. We present the approach and show that combining it with classic online RL methods make them perform as good as state of the art Offline RL algorithms such as CQL and BCQ. Finally, we show that using our method on top of established offline learning algorithms can improve them.