Periodic Q-learning

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 16
  • Download : 0
The use of target networks is a common practice in deep reinforcement learning for stabilizing the training; however, theoretical understanding of this technique is still limited. In this paper, we study the so-called periodic Q-learning algorithm (PQ-learning for short), which resembles the technique used in deep Q-learning for solving infinite-horizon discounted Markov decision processes (DMDP) in the tabular setting. PQ-learning maintains two separate Q-value estimates – the online estimate and target estimate. The online estimate follows the standard Q-learning update, while the target estimate is updated periodically. In contrast to the standard Q-learning, PQ-learning enjoys a simple finite time analysis and achieves better sample complexity for finding an epsilon-optimal policy. Our result provides a preliminary justification of the effectiveness of utilizing target estimates or networks in Q-learning algorithms.
Publisher
UC Berkeley
Issue Date
2020-06-11
Language
English
Citation

2nd Annual Conference on Learning for Dynamics and Control(L4DC)

URI
http://hdl.handle.net/10203/278704
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0