{ "agent": "GTD2", "environment": "Chain", "task": "EightStateOffPolicyRandomFeat", "number_of_runs": 50, "number_of_steps": 20000, "sub_sample": 1, "meta_parameters": { "alpha": [ 0.000003814, 0.000007629, 0.000015258, 0.000030517, 0.000061035, 0.000122070, 0.000244140, 0.000488281, 0.000976562, 0.001953125, 0.00390625, 0.0078125, 0.015625, 0.03125, 0.0625, 0.125, 0.25, 0.5, 1.0 ], "eta": [ 0.015625, 0.0625, 0.25, 1.0, 4.0, 16.0, 64.0, 256.0 ], "lmbda": [ 0.1, 0.2, 0.3 ] } }