Bias Correction and Confidence Intervals for Fitted Q-iteration

By Bibhas Chakraborty, Victor J. Strecher, Susan A. Murphy. 2008

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Eric B. Laber
2. Jesse Clifton
3. Chao Yu
4. Nathan Kallus
5. Pablo Escandell-Montero
6. Daniel J. Lizotte
7. Susan A. Murphy
8. Abiral Baniya

Citations in the corpus

• Batch Mode Reinforcement Learning based on the Synthesis of Artificial Trajectories (2012, background): “More theoretical works related with FQI have also been published (Munos and Szepesvári 2008; Chakraborty et al. 2008).”
• Q-Learning: Theory and Applications (2020, background): “In the case of Q-learning, we can achieve similar behavior—i.e., sampling from a distribution that concentrates on the”
• Impossibility Results for Nondifferentiable Functionals (2012, background): “Moodie and Richardson (2007) and Chakraborty, Strecher, and Murphy (2008) proposed bias-correction procedures.”
• Optimization of anemia treatment in hemodialysis patients via reinforcement learning (2014, background): “Second, narrow Hb target ranges recommended in clinical guidelines [10, 11], which need frequent dose changes.”