Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration

Dennis J.N.J. Soemers, Eric Piette, Matthew Stephenson, Cameron Browne

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)


Expert Iteration (ExIt) is an effective framework for learning game-playing policies from self-play. ExIt involves training a policy to mimic the search behaviour of a tree search algorithm-such as Monte-Carlo tree search-and using the trained policy to guide it. The policy and the tree search can then iteratively improve each other, through experience gathered in self-play between instances of the guided tree search algorithm. This paper outlines three different approaches for manipulating the distribution of data collected from self-play, and the procedure that samples batches for learning updates from the collected data. Firstly, samples in batches are weighted based on the durations of the episodes in which they were originally experienced. Secondly, Prioritized Experience Replay is applied within the ExIt framework, to prioritise sampling experience from which we expect to obtain valuable training signals. Thirdly, a trained exploratory policy is used to diversify the trajectories experienced in self-play. This paper summarises the effects of these manipulations on training performance evaluated in fourteen different board games. We find major improvements in early training performance in some games, and minor improvements averaged over fourteen games.

Original languageEnglish
Title of host publicationIEEE Conference on Games, CoG 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages8
ISBN (Electronic)9781728145334
ISBN (Print)9781728145341
Publication statusPublished - Aug 2020
Externally publishedYes
Event2020 IEEE Conference on Games, CoG 2020 - Virtual, Osaka, Japan
Duration: 24 Aug 202027 Aug 2020

Publication series

NameIEEE Conference on Computatonal Intelligence and Games, CIG
ISSN (Print)2325-4270
ISSN (Electronic)2325-4289


Conference2020 IEEE Conference on Games, CoG 2020
CityVirtual, Osaka


  • games
  • reinforcement learning
  • self-play
  • Expert Iteration (ExIt)
  • Prioritized Experience Replay


Dive into the research topics of 'Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration'. Together they form a unique fingerprint.

Cite this