@inproceedings{f301e42a906b447ab25c303ee10b1b41,
title = "Opposition-based Q(λ) with non-markovian update",
abstract = "The OQ(λ) algorithm benefits from an extension of eligibility traces introduced as opposition trace. This new technique is a combination of the idea of opposition and eligibility traces to deal with large state space problems in reinforcement learning applications. In our previous works the comparison of the results of OQ(λ) and conventional Watkins' Q(λ) reflected a remarkable increase in performance for the OQ(λ) algorithm. However the Markovian update of opposition traces is an issue which is investigated in this paper. It has been assumed that the opposite state can be presented to the agent. This may limit the usability of the technique to deterministic environments. In order to relax this assumption the Non-Markovian Opposition-Based Q(λ) (NOQ(λ)) is introduced in this work. The new method is a hybrid of Markovian update for eligibility traces and non-Markovian-based update for opposition traces. The experimental results show improvements of learning speed for the proposed technique compared to Q(λ) and OQ(λ). The new technique performs faster than OQ(λ) algorithm with the same success rate and can be employed for broader range of applications since it does not require determining state transition.",
author = "Maryam Shokri and Tizhoosh, {Hamid R.} and Kamel, {Mohamed S.}",
year = "2007",
doi = "10.1109/ADPRL.2007.368201",
language = "English (US)",
isbn = "1424407060",
series = "Proceedings of the 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007",
pages = "288--295",
booktitle = "Proceedings of the 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007",
note = "2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007 ; Conference date: 01-04-2007 Through 05-04-2007",
}