Generation of ice states through deep reinforcement learning
arXiv:1903.04698 · doi:10.1103/PhysRevE.99.062106
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 Carlo and benchmark against the baseline loop algorithm. This framework can be generalized to other models with topological constraints where generation of constraint-preserving states is difficult.
10 pages, 13 figures, 2 tables. Published version
References in corpus (10)
- Generative Adversarial Networks
- NICE: Non-linear Independent Components Estimation
- StarCraft II: A New Challenge for Reinforcement Learning
- Emergence of Locomotion Behaviours in Rich Environments
- Self-Learning Monte Carlo Method
- Breakdown of a topological phase: Quantum phase transition in a loop gas model with tension
- Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
- Markov Chain Monte Carlo Method without Detailed Balance
- An exact mapping between the Variational Renormalization Group and Deep Learning
- Simulating the Ising Model with a Deep Convolutional Generative Adversarial Network