Reinforcement Learning: A Tutorial Survey and Recent Advances

By Abhijit Gosavi. INFORMS journal on computing, 2009

357 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.

Reinforcement learning for control: Performance, stability, and deep approximators (2018, background): “Many books and survey papers have therefore been published on the topic, from equally varied perspectives: AI, where the classical textbook is that of Sutton and Barto (1998) with the second edition (Sutton and Barto, 2018), but also (Kaelbling et al., 1996; Gosavi, 2009; Szepesvári, 2010; Buşoniu e”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, background): “With respect to applications in solving dynamic optimization problems, Gosavi surveys Q-learning, temporal differences, semi-Markov decision problems, stochastic games, policy gradients, and hierarchical RL with detailed underlying mathematics [38].”
Deliberation for autonomous robots: A survey (2017, methodology): “Most approaches rely on learning an MDP policy, progressively improved with respect to a reward criterion [112, 205, 93].”
Reinforcement learning in robotic applications: a comprehensive survey (2021, neutral): “2017; Bertsekas 2018; Gosavi 2009).”
Online Model Learning Algorithms for Actor-Critic Control (2015, background): “General surveys on reinforcement learning already exist (Gosavi, 2009; Kaelbling et al., 1996; Szepesvári, 2010), but despite the growing popularity and recent developments in the field of actor-critic algorithms, no survey is specifically dedicated to them.”