Zap Q-Learning

By Adithya M. Devraj, Sean P. Meyn. 2017

100 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.

1. Sergey Levine
2. Abhishek Gupta
3. Aviral Kumar
4. Chelsea Finn
5. Pieter Abbeel
6. Michael Janner
7. Tianhe Yu
8. Ofir Nachum

Citations in the corpus

• DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction (2020, background): “Prior work on Q-learning and stochastic approximation analyzes time-varying μ, but either without function approximation (Watkins and Dayan, 1992; Tsitsiklis, 1994; Devraj and Meyn, 2017), or when fully online (Tsitsiklis and Roy, 1997), unlike our setting, that uses replay buffer data.”
• A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximation (2018, methodology): “Such a central limit theorem has been specifically provided for TD by Konda [2002] and Devraj and Meyn [2017].”
• Data-Enabled Predictive Control: In the Shallows of the DeePC (2018, methodology): “We begin with reinforcement learning approaches in which control actions are chosen to maximize a reward [16]–[19].”