2019
DOI: 10.1103/physreve.99.062106
|View full text |Cite
|
Sign up to set email alerts
|

Generation of ice states through deep reinforcement learning

Abstract: We present a deep reinforcement learning framework where a machine agent is trained to search for a policy to generate a ground state for the square ice model by exploring the physical environment. After training, the agent is capable of proposing a sequence of local moves to achieve the goal. Analysis of the trained policy and the state value function indicates that the ice rule and loop-closing condition are learned without prior knowledge. We test the trained policy as a sampler in the Markov chain Monte Ca… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
8
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 13 publications
(8 citation statements)
references
References 46 publications
0
8
0
Order By: Relevance
“…While an supervised approach is immediately successful at distinguishing the high and low temperature phases [14], unsupervised approaches did not succeed without an explicit recipe what type of restriction to look at. There has been significant progress in this direction, but a fully general approach is yet to be found [17][18][19][20][21][22][23][24]. While methods like principal component analysis, clustering and variational auto-encoders have proven to be successful to determine the phase transitions in spin models possessing an order parameter [25], systems without order parameters still represent a challenge.…”
Section: The Ising Gauge Theorymentioning
confidence: 99%
See 1 more Smart Citation
“…While an supervised approach is immediately successful at distinguishing the high and low temperature phases [14], unsupervised approaches did not succeed without an explicit recipe what type of restriction to look at. There has been significant progress in this direction, but a fully general approach is yet to be found [17][18][19][20][21][22][23][24]. While methods like principal component analysis, clustering and variational auto-encoders have proven to be successful to determine the phase transitions in spin models possessing an order parameter [25], systems without order parameters still represent a challenge.…”
Section: The Ising Gauge Theorymentioning
confidence: 99%
“…In figure 2 we show how the difference between the true and predicted inverse temperatures β pred −β label behaves as a function of the true β label for seven different system sizes N=4, 8,12,16,20,24,28 (the total number of spins is 2N 2 ). We see that the behavior of the prediction is not uniform for all inputs and, in fact, we observe that for all systems sizes there exists a different finiteb above which the network has difficulties to identify the correct β label .…”
Section: The Ising Gauge Theorymentioning
confidence: 99%
“…Deep reinforcement learning has also been used in conjunction with MC simulations [186]. Zhao et al develop a deep reinforcement learning framework where a machine agent is trained to search for a policy to generate ground states for the square ice model [187], which belongs to the family of ice models used to describe the statistical properties of the hydrogen atoms in water ice.…”
Section: Machine Learning Acceleration Of Monte Carlo Simulationsmentioning
confidence: 99%
“…Another approach is 'self-learning Monte Carlo' [18][19][20][21] that, in principle, works for any generic system and applies machinelearning-based approaches on top of MCMC to speed up the simulations and to reduce the increase in auto-correlation time near the critical temperature. Other approaches which apply machine-learning techniques as a supplement or alternative to MCMC are based on normalizing flow [22], Boltzmann machines [23][24][25][26], on reinforcement learning [27], on generative adversarial networks (GANs) [28][29][30][31][32][33], autoencoders [34][35][36], and on variational autoregressive networks [37][38][39][40].…”
Section: Introductionmentioning
confidence: 99%