Q-learning

Known as: Q learning 
Q-learning is a model-free reinforcement learning technique. Specifically, Q-learning can be used to find an optimal action-selection policy for any… (More)
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2016
Highly Cited
2016
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known… (More)
  • figure 1
  • figure 2
  • table 1
  • figure 3
  • figure 4
Is this relevant?
Review
2016
Review
2016
Cognitive radio sensor networks are one of the kinds of application where cognitive techniques can be adopted and have many… (More)
Is this relevant?
Highly Cited
2003
Highly Cited
2003
We extend Q-learning to a noncooperative multiagent context, using the framework of generalsum stochastic games. A learning agent… (More)
  • table 1
  • table 2
  • figure 1
  • figure 2
  • figure 3
Is this relevant?
Highly Cited
2003
Highly Cited
2003
There have been several attempts to design multiagent Q-learning algorithms capable of learning equilibrium policies in general… (More)
  • table 1
  • figure 1
  • figure 2
  • table 2
  • figure 4
Is this relevant?
Highly Cited
2001
Highly Cited
2001
In this paper we derive convergence rates for Q-learning. We show an interesting relationship between the convergence rate and… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
Is this relevant?
Highly Cited
1998
Highly Cited
1998
A central problem in learning in complex environments is balancing exploration of untested actions against exploitation of… (More)
  • figure 1
  • figure 2
  • figure 3
  • table 1
  • figure 4
Is this relevant?
Highly Cited
1994
Highly Cited
1994
Reinforcement learning algorithms are a powerful machine learning technique. However, much of the work on these algorithms has… (More)
Is this relevant?
Highly Cited
1994
Highly Cited
1994
We provide some general results on the convergence of a class of stochastic approximation algorithms and their parallel and… (More)
Is this relevant?
Highly Cited
1994
Highly Cited
1994
This paper presents a novel incremental algorithm that combines Q-learning, a well-known dynamic-programming based reinforcement… (More)
Is this relevant?
Highly Cited
1992
Highly Cited
1992
$$\mathcal{Q}$$ -learning (Watkins, 1989) is a simple way for agents to learn how to act optimally in controlled Markovian… (More)
Is this relevant?