Boosted Fitted Q-Iteration

By Samuele Tosatto, Matteo Pirotta, Carlo D'Eramo, Marcello Restelli. 2017

49 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Fitted Q-Learning for Relational Domains (2020, methodology): “Our approach uses gradient boosting where we learn sets of conjunctive features as paths from the root to the leaf of each RRT and lift the arguments of ﬁtted Q-learning in propositional domains (Ernst, Geurts, and Wehenkel 2005; Tosatto et al. 2017) to relational domains.”
Diagnosing Bottlenecks in Deep Q-learning Algorithms (2019, background): “Munos & Szepesvári (2008); Maillard et al. (2010); Tosatto et al. (2017) provide such PAC-bounds which account for sampling error in the context of Q-learning and value-based methods, and quantify the quality of the final solution in terms of sample complexity.”
Information-Theoretic Considerations in Batch Reinforcement Learning (2019, methodology): “Existing works that analyze error propagation and finite sample behavior of ADP methods (Munos, 2003; Szepesvári & Munos, 2005; Antos et al., 2008; Munos & Szepesvári, 2008; Tosatto et al., 2017) have provided us with a decent understanding: To guarantee sample-efficient learning of near-optimal pol”
Instabilities of Offline RL with Pre-Trained Neural Representation (2021, background): “Let us start by considering when we expect oﬄine RL to be successful from a theoretical perspective [Munos, 2003, Szepesv´ari and Munos, 2005, Antos et al., 2008, Munos and Szepesv´ari, 2008, Tosatto et al., 2017, Chen and Jiang, 2019, Duan et al., 2020].”
What are the Statistical Limits of Offline RL with Linear Function Approximation? (2020, background): “Existing works [Munos, 2003, Szepesvári and Munos, 2005, Antos et al., 2008, Munos and Szepesvári, 2008, Tosatto et al., 2017, Xie and Jiang, 2020b] that analyze the sample complexity of approximate dynamic programming-based approaches usually make the following two categories of assumptions: (i)…”
Provably Efficient Exploration in Policy Optimization (2019, background): “, 2018a;b; Wainwright, 2019) or finite concentratability coefficients (Munos & Szepesvári, 2008; Antos et al., 2008; Farahmand et al., 2010; Tosatto et al., 2017; Yang et al., 2019b; Chen & Jiang, 2019), both of which are often unavailable in practice.”
Iterative Value-Aware Model Learning (2018, background): “…Szepesvári and Smart, 2004, Ernst et al., 2005, Munos and Szepesvári, 2008, Farahmand et al., 2009, Farahmand and Precup, 2012, Mnih et al., 2015, Tosatto et al., 2017, Farahmand et al., 2017b] or (Approximate) Policy Iteration (API) algorithms [Lagoudakis and Parr, 2003, Antos et al., 2008,…”
Boosted Curriculum Reinforcement Learning (2022, background): “The benefit of the boosting framework is that it is well understood from a theoretical perspective (Tosatto et al., 2017), allowing for the derivation of error bounds, as also presented in this paper.”
A Geometric Perspective on Optimal Representations for Reinforcement Learning (2019, unknown): “, 2016), and nonparametric methods (Ernst et al., 2005; Farahmand et al., 2016; Tosatto et al., 2017).”
A Theoretical Analysis of Deep Q-Learning (2019, background): “Furthermore, various extensions of FQI are studied in Antos et al. (2008a); Farahmand et al. (2009); Tosatto et al. (2017) to handle continuous actions space and ensemble learning.”