Finite-sample Analysis of Bellman Residual Minimization

How researchers see this paper

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

Information-Theoretic Considerations in Batch Reinforcement Learning (2019, methodology): “1 In this paper, we restrict ourselves to the so-called one-path setting and do not allow multiple samples from the same state (Sutton & Barto, 1998; Maillard et al., 2010), which is only feasible in certain simulated environments and allows algorithms to succeed with realizability as the only…”
Regularization in reinforcement learning (2011, methodology): “When the generative model is available and the double-sampling is not an issue, Maillard et al. [2010] analyze BRM for the finite linear function spaces.”
Transfer in Reinforcement Learning: A Framework and a Survey (2012, background): “…as fitted value iteration (Munos and Szepesvári, 2008), LSTD (Farahmand et al, 2008; Lazaric et al, 2010), and Bellman residual minimization (Antos et al, 2008; Maillard et al, 2010), at the best of our knowledge, at the moment there is no finite-sample analysis for any transfer algorithm in RL.”
Action-Gap Phenomenon in Reinforcement Learning (2011, background): “[14], who mainly focused on the quality of the (action-)value function estimate and ignored the action-gap regularity.”