We study two-dimensional Ising spins, evolving through reinforcement learning using their state, action, and reward. The state of a spin is defined as whether it is in the majority or minority with its nearest neighbours. The spin updates its state using an { \epsilon}-greedy algorithm. The parameter { \epsilon} plays the role equivalent to the temperature in the Ising model. We find a phase transition from long-ranged ordered to a disordered state as we tune { \epsilon} from small to large values. In analogy with the phase transition in the Ising model, we calculate the critical { \epsilon} and the three critical exponents { \beta}, { \gamma}, { \nu} of magnetization, susceptibility, and correlation length, respectively. A hyper-scaling relation d{ \nu} = 2{ \beta} + { \gamma} is obtained between the three exponents. The system is studied for different learning rates. The exponents approach the exact values for two-dimensional Ising model for lower learning rates.
Categories: cond-mat.stat-mech