An empirical evaluation of interval estimation for Markov decision processes

By Alexander L. Strehl, Michael L. Littman. 2004

69 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.

In Artificial Intelligence

Citations in the corpus

Informing sequential clinical decision-making through reinforcement learning: an empirical study (2010, background): “For example, in (Kaelbling et al. 1996), (Strehl and Littman 2004), and (Strehl and Littman 2005), measures of confidence are used to guide exploration.”
Offline Evaluation of Online Reinforcement Learning Algorithms (2016, methodology): “Then, for each evaluator (PSRS and model-based) we sampled 100 different datasets of 100 episodes from SixArms us-ing a uniform sampling policy.”
Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains (2010, methodology): “The Model Based Interval Estimation Algorithm (MBIE) uses upper confidence bounds on the model transition probabilities to select the model that gives the maximal reward [22].”
Count-Based Exploration in Feature Space for Reinforcement Learning (2017, methodology): “While tabular OFU algorithms perform well in practice on small MDPs [Strehl and Littman, 2004], their sample complexity becomes prohibitive for larger problems [Kakade, 2003].”
An analysis of model-based Interval Estimation for Markov Decision Processes (2008, background): “We report results for two simple MDPs, both taken from [19].”
Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning (2006, methodology): “interval estimation [10, 11], action elimination [12], or PAC-learning [6].”
A theoretical analysis of Model-Based Interval Estimation (2005, methodology): “Equation 6 can be solved efficiently using value iteration (Strehl & Littman, 2004).”