Built on

“Accelerating Self-Play Learning in Go”, 2020
Original
David. Wu · 1902
Earlier work this paper cites.
“ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero”, 2019
Original
Yuandong Tian et al · 1902
Earlier work this paper cites.
“Accelerating Reinforcement Learning through GPU Atari Emulation”, 2020
Original
Steven Dalton, Iuri Frosio and Michael Garland · 1907
Earlier work this paper cites.
“OpenSpiel: A Framework for Reinforcement Learning in Games”, 2020
Original
OpenSpiel Contributors · 1908
Earlier work this paper cites.
“Multiagent Evaluation under Incomplete Information”, 2020
Original
Mark Rowland et al · 1909
Earlier work this paper cites.
“Dota 2 with Large Scale Deep Reinforcement Learning”, 2019
Original
OpenAI et al · 1912
Earlier work this paper cites.
“Vil de laere Polygon?”
Piet Hein · 1942
Earlier work this paper cites.
“The rating of chessplayers, past and present”
Arpad Elo · 1978
Earlier work this paper cites.
“Optimal nonlinear approximation”
Ronald DeVore, Ralph Howard and Charles Micchelli · 1989
Earlier work this paper cites.
“The glicko system”
Mark Glickman · 1995
Earlier work this paper cites.
“Polygames: Improved Zero Learning”, 2020
Original
Tristan Cazenave et al · 2001
Earlier work this paper cites.
“Real World Games Look Like Spinning Tops”, 2020
Original
Wojciech Czarnecki et al · 2004
Earlier work this paper cites.
“Trueskill tm: a Bayesian skill rating system”
T Minka, T Graepel and R Herbrich · 2007
Earlier work this paper cites.
“Monte-Carlo Tree Search as Regularized Policy Optimization”, 2020
Original
Jean-Bastien Grill et al · 2007
Earlier work this paper cites.
“IPython: a System for Interactive Scientific Computing”
Fernando Pérez and Brian. Granger · 2007
Earlier work this paper cites.
“Matplotlib: A 2D graphics environment”
J.. Hunter · 2007
Earlier work this paper cites.
“Phasic Policy Gradient”, 2020
Original
Karl Cobbe, Jacob Hilton, Oleg Klimov and John Schulman · 2009
Earlier work this paper cites.

Similar

“MoHex 2.0: a pattern-based MCTS Hex player”
Shih-Chieh Huang et al · 2013
Cited alongside, same era.
“Scalable parallel DFPN search”
Jakub Pawlewicz and Ryan Hayward · 2013
Cited alongside, same era.
“Stronger virtual connections in hex”
Jakub Pawlewicz, Ryan Hayward, Philip Henderson and Broderick Arneson · 2014
Cited alongside, same era.
“Neurohex: A deep q-learning hex agent”
Kenny Young, Gautham Vasan and Ryan Hayward · 2016
Cited alongside, same era.
“Deep learning scaling is predictable, empirically”
Original
Joel Hestness et al · 2017
Cited alongside, same era.
“Thinking fast and slow with deep learning and tree search”
Original
Thomas Anthony, Zheng Tian and David Barber · 2017

Then

“National Research Cloud Call To Action”, 2020
NRC Letter Signatories · 2020
Later among the works it cites.
“Scaling laws for neural language models”
Original
Jared Kaplan et al · 2020
Later among the works it cites.
“Scaling laws for autoregressive generative modeling”
Original
Tom Henighan et al · 2020
Later among the works it cites.
“On the Predictability of Pruning Across Scales”
Original
Jonathan Rosenfeld, Jonathan Frankle, Michael Carbin and Nir Shavit · 2020
Later among the works it cites.
“Hex — Wikipedia, The Free Encyclopedia”, 2020
Wikipedia contributors · 2020
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2021

Scaling Scaling Laws with Board Games

Jones, Andy L.

Understand

The largest experiments in machine learning now require resources far beyond the budget of all but a few institutions.

Fortunately, it has recently been shown that the results of these huge experiments can often be extrapolated from the results of a sequence of far smaller, cheaper experiments.
In this work, we show that not only can the extrapolation be done based on the size of the model, but on the size of the problem as well.
By conducting a sequence of experiments using AlphaZero and Hex, we show that the performance achievable with a fixed amount of compute degrades predictably as the game gets larger and harder.

Built on

“Accelerating Self-Play Learning in Go”, 2020
Original
David. Wu · 1902
Earlier work this paper cites.
“ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero”, 2019
Original
Yuandong Tian et al · 1902
Earlier work this paper cites.
“Accelerating Reinforcement Learning through GPU Atari Emulation”, 2020
Original
Steven Dalton, Iuri Frosio and Michael Garland · 1907
Earlier work this paper cites.
“OpenSpiel: A Framework for Reinforcement Learning in Games”, 2020
Original
OpenSpiel Contributors · 1908
Earlier work this paper cites.
“Multiagent Evaluation under Incomplete Information”, 2020
Original
Mark Rowland et al · 1909
Earlier work this paper cites.
“Dota 2 with Large Scale Deep Reinforcement Learning”, 2019
Original
OpenAI et al · 1912
Earlier work this paper cites.
“Vil de laere Polygon?”
Piet Hein · 1942
Earlier work this paper cites.
“The rating of chessplayers, past and present”
Arpad Elo · 1978
Earlier work this paper cites.
“Optimal nonlinear approximation”
Ronald DeVore, Ralph Howard and Charles Micchelli · 1989
Earlier work this paper cites.
“The glicko system”
Mark Glickman · 1995
Earlier work this paper cites.
“Polygames: Improved Zero Learning”, 2020
Original
Tristan Cazenave et al · 2001
Earlier work this paper cites.
“Real World Games Look Like Spinning Tops”, 2020
Original
Wojciech Czarnecki et al · 2004
Earlier work this paper cites.
“Trueskill tm: a Bayesian skill rating system”
T Minka, T Graepel and R Herbrich · 2007
Earlier work this paper cites.
“Monte-Carlo Tree Search as Regularized Policy Optimization”, 2020
Original
Jean-Bastien Grill et al · 2007
Earlier work this paper cites.
“IPython: a System for Interactive Scientific Computing”
Fernando Pérez and Brian. Granger · 2007
Earlier work this paper cites.
“Matplotlib: A 2D graphics environment”
J.. Hunter · 2007
Earlier work this paper cites.
“Phasic Policy Gradient”, 2020
Original
Karl Cobbe, Jacob Hilton, Oleg Klimov and John Schulman · 2009
Earlier work this paper cites.

Similar

“MoHex 2.0: a pattern-based MCTS Hex player”
Shih-Chieh Huang et al · 2013
Cited alongside, same era.
“Scalable parallel DFPN search”
Jakub Pawlewicz and Ryan Hayward · 2013
Cited alongside, same era.
“Stronger virtual connections in hex”
Jakub Pawlewicz, Ryan Hayward, Philip Henderson and Broderick Arneson · 2014
Cited alongside, same era.
“Neurohex: A deep q-learning hex agent”
Kenny Young, Gautham Vasan and Ryan Hayward · 2016
Cited alongside, same era.
“Deep learning scaling is predictable, empirically”
Original
Joel Hestness et al · 2017
Cited alongside, same era.
“Thinking fast and slow with deep learning and tree search”
Original
Thomas Anthony, Zheng Tian and David Barber · 2017

Then

“National Research Cloud Call To Action”, 2020
NRC Letter Signatories · 2020
Later among the works it cites.
“Scaling laws for neural language models”
Original
Jared Kaplan et al · 2020
Later among the works it cites.
“Scaling laws for autoregressive generative modeling”
Original
Tom Henighan et al · 2020
Later among the works it cites.
“On the Predictability of Pruning Across Scales”
Original
Jonathan Rosenfeld, Jonathan Frankle, Michael Carbin and Nir Shavit · 2020
Later among the works it cites.
“Hex — Wikipedia, The Free Encyclopedia”, 2020
Wikipedia contributors · 2020
Later among the works it cites.