A Generalised Method for Empirical Game Theoretic Analysis · HackerPapers discussions

A Generalised Method for Empirical Game Theoretic Analysis — HN submission

Sun, 20 Mar 2022 21:23:30 GMT

A Generalised Method for Empirical Game Theoretic Analysis (2018)

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

A Generalised Method for Empirical Game Theoretic Analysis — mentioned by gwern

Thu, 06 Dec 2018 21:49:58 GMT

https://arxiv.org/abs/1806.02643 and https://arxiv.org/abs/1803.06376 (as does the choice to drop the checkpoints & historical self-plays in general from the training) indicate that AlphaGo versions, at least up until then, tend to be transitive: > What is worthwhile to observe from the AlphaGo dataset, and illustrated as a series in Figures 3 and 4, is that there is clearly an incremental increase in the strength of the AlphaGo algorithm going from version αr to αrvp, building on previous strengths, without any intransitive behaviour occurring, when only considering a strategy space formed…

Paper and discussion history. A mention is not an endorsement.

A Generalised Method for Empirical Game Theoretic Analysis — mentioned by dharma1

Mon, 07 May 2018 17:11:25 GMT

I don't know what I would model or how - that's why I was asking for pointers :) And I in addition to economists, I would be interested in seeing contributions from physicists, computer scientists and machine learning researchers. This paper was super interesting - https://arxiv.org/abs/1706.03058, as was this - https://arxiv.org/abs/1803.06376 But would like to see UBI specific papers.

Paper and discussion history. A mention is not an endorsement.