def test_monte_carlo(iterations=1000000, n0=100): print "\n-------------------" print "Monte Carlo control" print "run for n. iterations: " + str(iterations) print "win percentage: " # learn game = Environment() agent = Agent(game, n0) agent.MC_control(iterations) # plot and store agent.show_statevalue_function() agent.store_Qvalue_function()
def test_mc_control(iter=50000, n0=100): agent = Agent() agent.MC_control(iter, n0) agent.plot_state()