{ "name": "root", "gauges": { "BensonV4.Policy.Entropy.mean": { "value": 1.3508883714675903, "min": 1.3445194959640503, "max": 1.3667104244232178, "count": 5 }, "BensonV4.Policy.Entropy.sum": { "value": 13589.9375, "min": 12181.3466796875, "max": 13776.44140625, "count": 5 }, "BensonV4.Step.mean": { "value": 3759941.0, "min": 3719953.0, "max": 3759941.0, "count": 5 }, "BensonV4.Step.sum": { "value": 3759941.0, "min": 3719953.0, "max": 3759941.0, "count": 5 }, "BensonV4.Policy.ExtrinsicValueEstimate.mean": { "value": 1.5055700540542603, "min": 1.4554778337478638, "max": 1.5631643533706665, "count": 5 }, "BensonV4.Policy.ExtrinsicValueEstimate.sum": { "value": 295.09173583984375, "min": 265.7379455566406, "max": 299.07958984375, "count": 5 }, "BensonV4.Environment.EpisodeLength.mean": { "value": 151.27272727272728, "min": 150.1076923076923, "max": 152.33846153846153, "count": 5 }, "BensonV4.Environment.EpisodeLength.sum": { "value": 9984.0, "min": 8164.0, "max": 10019.0, "count": 5 }, "BensonV4.Environment.CumulativeReward.mean": { "value": 5.765378269409253, "min": 5.6894510709322414, "max": 5.897744768747577, "count": 5 }, "BensonV4.Environment.CumulativeReward.sum": { "value": 380.5149657810107, "min": 318.47821751236916, "max": 384.8610228523612, "count": 5 }, "BensonV4.Policy.ExtrinsicReward.mean": { "value": 5.765378269409253, "min": 5.6894510709322414, "max": 5.897744768747577, "count": 5 }, "BensonV4.Policy.ExtrinsicReward.sum": { "value": 380.5149657810107, "min": 318.47821751236916, "max": 384.8610228523612, "count": 5 }, "BensonV4.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "BensonV4.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "BensonV4.Losses.PolicyLoss.mean": { "value": 0.11566021161525575, "min": 0.1076902610879454, "max": 0.11566021161525575, "count": 4 }, "BensonV4.Losses.PolicyLoss.sum": { "value": 0.11566021161525575, "min": 0.1076902610879454, "max": 0.11566021161525575, "count": 4 }, "BensonV4.Losses.ValueLoss.mean": { "value": 0.04978977781373851, "min": 0.04331555476609042, "max": 0.04978977781373851, "count": 4 }, "BensonV4.Losses.ValueLoss.sum": { "value": 0.04978977781373851, "min": 0.04331555476609042, "max": 0.04978977781373851, "count": 4 }, "BensonV4.Policy.LearningRate.mean": { "value": 7.485721504761999e-05, "min": 7.485721504761999e-05, "max": 7.670917443029998e-05, "count": 4 }, "BensonV4.Policy.LearningRate.sum": { "value": 7.485721504761999e-05, "min": 7.485721504761999e-05, "max": 7.670917443029998e-05, "count": 4 }, "BensonV4.Policy.Epsilon.mean": { "value": 0.12495237999999999, "min": 0.12495237999999999, "max": 0.1255697, "count": 4 }, "BensonV4.Policy.Epsilon.sum": { "value": 0.12495237999999999, "min": 0.12495237999999999, "max": 0.1255697, "count": 4 }, "BensonV4.Policy.Beta.mean": { "value": 0.012483694761999998, "min": 0.012483694761999998, "max": 0.012792293029999995, "count": 4 }, "BensonV4.Policy.Beta.sum": { "value": 0.012483694761999998, "min": 0.012483694761999998, "max": 0.012792293029999995, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713539163", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\noahk\\Documents\\Unity projects\\ML Tutorual v2\\ml-agents\\.venv\\Scripts\\mlagents-learn config/BensonV4.yaml --run-id=BensonV4 --resume", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1713539310" }, "total": 146.8465324, "count": 1, "self": 0.0043030999999871256, "children": { "run_training.setup": { "total": 0.07616970000000012, "count": 1, "self": 0.07616970000000012 }, "TrainerController.start_learning": { "total": 146.7660596, "count": 1, "self": 0.1163909999995667, "children": { "TrainerController._reset_env": { "total": 10.3584175, "count": 1, "self": 10.3584175 }, "TrainerController.advance": { "total": 136.13096090000042, "count": 6858, "self": 0.10552590000048667, "children": { "env_step": { "total": 102.59305809999964, "count": 6858, "self": 77.66245159999988, "children": { "SubprocessEnvManager._take_step": { "total": 24.854691299999992, "count": 6859, "self": 0.3053916000001422, "children": { "TorchPolicy.evaluate": { "total": 24.54929969999985, "count": 6607, "self": 24.54929969999985 } } }, "workers": { "total": 0.07591519999976626, "count": 6858, "self": 0.0, "children": { "worker_root": { "total": 120.62309139999942, "count": 6858, "is_parallel": true, "self": 65.5113897999996, "children": { "steps_from_proto": { "total": 0.0021694000000014313, "count": 2, "is_parallel": true, "self": 0.0008578999999944159, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013115000000070154, "count": 12, "is_parallel": true, "self": 0.0013115000000070154 } } }, "UnityEnvironment.step": { "total": 55.10953219999982, "count": 6858, "is_parallel": true, "self": 0.7230074999996319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.7702295999999382, "count": 6858, "is_parallel": true, "self": 0.7702295999999382 }, "communicator.exchange": { "total": 51.2747549, "count": 6858, "is_parallel": true, "self": 51.2747549 }, "steps_from_proto": { "total": 2.3415402000002548, "count": 6858, "is_parallel": true, "self": 0.9429467000018548, "children": { "_process_rank_one_or_two_observation": { "total": 1.3985934999984, "count": 41148, "is_parallel": true, "self": 1.3985934999984 } } } } } } } } } } }, "trainer_advance": { "total": 33.43237690000029, "count": 6858, "self": 0.18423370000056138, "children": { "process_trajectory": { "total": 5.548114599999716, "count": 6858, "self": 5.548114599999716 }, "_update_policy": { "total": 27.700028600000017, "count": 5, "self": 5.631023199999724, "children": { "TorchPPOOptimizer.update": { "total": 22.069005400000293, "count": 2463, "self": 22.069005400000293 } } } } } } }, "trainer_threads": { "total": 7.000000152856956e-07, "count": 1, "self": 7.000000152856956e-07 }, "TrainerController._save_models": { "total": 0.16028950000000464, "count": 1, "self": 0.00573789999998553, "children": { "RLTrainer._checkpoint": { "total": 0.1545516000000191, "count": 1, "self": 0.1545516000000191 } } } } } } }