Bernardo Ávila Pires

Multiclass Classification Calibration Functions pdf

Csaba Szepesvári, Bernardo Ávila Pires, Csaba Szepesvari, 2016, ArXiv.

Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models

Bernardo Ávila Pires, B. '. Pires, 2016, COLT.

Toward Practical Reinforcement Learning Algorithms: Classification Based Policy Iteration and Model-Based Learning

Bernardo Ávila Pires, B. '. Pires, 2017 .

Pseudo-MDPs and factored linear action models

Xinhua Zhang, Csaba Szepesvári, Bernardo Ávila Pires, 2014, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL).

Cost-sensitive Multiclass Classification Risk Bounds

Csaba Szepesvári, Mohammad Ghavamzadeh, Bernardo Ávila Pires, 2013, ICML.

Pathological Effects of Variance on Classification-Based Policy Iteration

Csaba Szepesvári, Bernardo Ávila Pires, Csaba Szepesvari, 2015, AAAI Workshop: Learning for General Competency in Video Games.

Statistical linear estimation with penalized estimators: an application to reinforcement learning

Csaba Szepesvári, Bernardo Ávila Pires, Csaba Szepesvari, 2012, ICML.