@article { santos20,
	abstract = {In this work, we identify a novel set of conditions that ensure convergence with probability 1 of Q-learning with linear function approximation, by proposing a two time-scale variation thereof. In the faster time scale, the algorithm features an update similar to that of DQN, where the impact of bootstrapping is attenuated by using a Q-value estimate akin to that of the target network in DQN. The slower time-scale, in turn, can be seen as a modified target network update. We establish the convergence of our algorithm, provide an error bound and discuss our results in light of existing convergence results on reinforcement learning with function approximation. Finally, we illustrate the convergent behavior of our method in domains where standard Q-learning has previously been shown to diverge.
},
	journal = {Advances in Neural Information Processing Systems},
	keywords = {Reinforcement Learning;},
	title = {A new convergent variant of Q-learning with linear function approximation},
	volume = {33},
	year = {2020},
	author = {Diogo S. Carvalho, Francisco S. Melo, Pedro A. Santos}
}