{ "name": "root", "gauges": { "BensonImitationV2.Policy.Entropy.mean": { "value": 0.21836252510547638, "min": 0.21836252510547638, "max": 1.4134068489074707, "count": 102 }, "BensonImitationV2.Policy.Entropy.sum": { "value": 2278.17626953125, "min": 2271.458984375, "max": 14594.8388671875, "count": 102 }, "BensonImitationV2.Step.mean": { "value": 1019966.0, "min": 9999.0, "max": 1019966.0, "count": 102 }, "BensonImitationV2.Step.sum": { "value": 1019966.0, "min": 9999.0, "max": 1019966.0, "count": 102 }, "BensonImitationV2.Policy.ExtrinsicValueEstimate.mean": { "value": 0.874127984046936, "min": 0.42324298620224, "max": 1.7607990503311157, "count": 102 }, "BensonImitationV2.Policy.ExtrinsicValueEstimate.sum": { "value": 139.8604736328125, "min": 69.41184997558594, "max": 287.01025390625, "count": 102 }, "BensonImitationV2.Policy.CuriosityValueEstimate.mean": { "value": 0.21148701012134552, "min": 0.14661255478858948, "max": 4.431127548217773, "count": 102 }, "BensonImitationV2.Policy.CuriosityValueEstimate.sum": { "value": 33.837921142578125, "min": 23.60462188720703, "max": 708.9804077148438, "count": 102 }, "BensonImitationV2.Policy.GailValueEstimate.mean": { "value": 30.597423553466797, "min": 10.18994140625, "max": 38.712249755859375, "count": 102 }, "BensonImitationV2.Policy.GailValueEstimate.sum": { "value": 4895.587890625, "min": 1660.96044921875, "max": 6232.67236328125, "count": 102 }, "BensonImitationV2.Environment.EpisodeLength.mean": { "value": 926.0, "min": 406.47058823529414, "max": 1105.8, "count": 102 }, "BensonImitationV2.Environment.EpisodeLength.sum": { "value": 8334.0, "min": 3221.0, "max": 14548.0, "count": 102 }, "BensonImitationV2.Environment.CumulativeReward.mean": { "value": 8.785778889096239, "min": 0.994647218099357, "max": 12.216501230583527, "count": 102 }, "BensonImitationV2.Environment.CumulativeReward.sum": { "value": 79.07201000186615, "min": 16.90900270768907, "max": 147.37601834966335, "count": 102 }, "BensonImitationV2.Policy.ExtrinsicReward.mean": { "value": 8.785778889096239, "min": 0.994647218099357, "max": 12.216501230583527, "count": 102 }, "BensonImitationV2.Policy.ExtrinsicReward.sum": { "value": 79.07201000186615, "min": 16.90900270768907, "max": 147.37601834966335, "count": 102 }, "BensonImitationV2.Policy.CuriosityReward.mean": { "value": 1.7365858786377228, "min": 0.7789605254656635, "max": 29.635238213574183, "count": 102 }, "BensonImitationV2.Policy.CuriosityReward.sum": { "value": 15.629272907739505, "min": 10.094776071608067, "max": 503.79904963076115, "count": 102 }, "BensonImitationV2.Policy.GailReward.mean": { "value": 328.5199515654224, "min": 115.95333948415646, "max": 406.2315421423991, "count": 102 }, "BensonImitationV2.Policy.GailReward.sum": { "value": 2956.6795640888013, "min": 1147.901626907289, "max": 5077.607989122145, "count": 102 }, "BensonImitationV2.Losses.PolicyLoss.mean": { "value": 0.17667413760630996, "min": 0.1677064943613938, "max": 0.1981561970553415, "count": 102 }, "BensonImitationV2.Losses.PolicyLoss.sum": { "value": 0.8833706880315497, "min": 0.6783060911556471, "max": 0.9394539042504082, "count": 102 }, "BensonImitationV2.Losses.ValueLoss.mean": { "value": 4.507527624265537, "min": 1.8594956072925808, "max": 6.4784139271326975, "count": 102 }, "BensonImitationV2.Losses.ValueLoss.sum": { "value": 22.53763812132768, "min": 8.837262982431636, "max": 28.696687943530815, "count": 102 }, "BensonImitationV2.Policy.LearningRate.mean": { "value": 0.00019847217384262, "min": 0.00019847217384262, "max": 0.00029947692517435837, "count": 102 }, "BensonImitationV2.Policy.LearningRate.sum": { "value": 0.0009923608692131, "min": 0.0008060602313132999, "max": 0.0014926282024572668, "count": 102 }, "BensonImitationV2.Policy.Epsilon.mean": { "value": 0.09999999999999999, "min": 0.09999999999999998, "max": 0.09999999999999999, "count": 102 }, "BensonImitationV2.Policy.Epsilon.sum": { "value": 0.49999999999999994, "min": 0.3999999999999999, "max": 0.49999999999999994, "count": 102 }, "BensonImitationV2.Policy.Beta.mean": { "value": 0.03308207426200001, "min": 0.03308207426200001, "max": 0.04991283826916666, "count": 102 }, "BensonImitationV2.Policy.Beta.sum": { "value": 0.16541037131000003, "min": 0.13435648133000003, "max": 0.24877161239333334, "count": 102 }, "BensonImitationV2.Losses.CuriosityForwardLoss.mean": { "value": 0.06405584294230482, "min": 0.0409978992705546, "max": 0.47139101573493875, "count": 102 }, "BensonImitationV2.Losses.CuriosityForwardLoss.sum": { "value": 0.3202792147115241, "min": 0.1639915970822184, "max": 1.885564062939755, "count": 102 }, "BensonImitationV2.Losses.CuriosityInverseLoss.mean": { "value": 0.24426068489402838, "min": 0.24426068489402838, "max": 1.577752122109906, "count": 102 }, "BensonImitationV2.Losses.CuriosityInverseLoss.sum": { "value": 1.221303424470142, "min": 1.0455760290679466, "max": 6.311008488439624, "count": 102 }, "BensonImitationV2.Policy.GAILPolicyEstimate.mean": { "value": 0.3275273488723356, "min": 0.213526945689439, "max": 0.40045476305927946, "count": 102 }, "BensonImitationV2.Policy.GAILPolicyEstimate.sum": { "value": 1.637636744361678, "min": 1.067634728447195, "max": 2.0022738152963973, "count": 102 }, "BensonImitationV2.Policy.GAILExpertEstimate.mean": { "value": 0.6728636744192209, "min": 0.595639054947221, "max": 0.7535881714494276, "count": 102 }, "BensonImitationV2.Policy.GAILExpertEstimate.sum": { "value": 3.3643183720961045, "min": 2.442071112744067, "max": 3.767940857247138, "count": 102 }, "BensonImitationV2.Losses.GAILLoss.mean": { "value": 0.9010745458359235, "min": 0.6332013434305961, "max": 1.1040863118158293, "count": 102 }, "BensonImitationV2.Losses.GAILLoss.sum": { "value": 4.5053727291796175, "min": 3.062521615840808, "max": 5.520431559079147, "count": 102 }, "BensonImitationV2.Policy.GAILGradMagLoss.mean": { "value": 0.04573705959232415, "min": 0.024298097816637942, "max": 0.7750102781219907, "count": 102 }, "BensonImitationV2.Policy.GAILGradMagLoss.sum": { "value": 0.22868529796162076, "min": 0.09719239126655177, "max": 3.100041112487963, "count": 102 }, "BensonImitationV2.Losses.PretrainingLoss.mean": { "value": 0.05488089387391741, "min": 0.054411157006899705, "max": 0.4469718710070715, "count": 102 }, "BensonImitationV2.Losses.PretrainingLoss.sum": { "value": 0.27440446936958707, "min": 0.21936922012367566, "max": 1.787887484028286, "count": 102 }, "BensonImitationV2.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 102 }, "BensonImitationV2.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 102 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712910414", "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/BensonImitationV2.yaml --run-id=BensonImitationV2 --force --env=C:\\Users\\noahk\\Desktop\\BensonV2\\Racesm_L.exe --no-graphics --num-envs=10", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1712914871" }, "total": 4456.4355384, "count": 1, "self": 0.0063904000007823925, "children": { "run_training.setup": { "total": 0.7543147000000001, "count": 1, "self": 0.7543147000000001 }, "TrainerController.start_learning": { "total": 4455.6748333, "count": 1, "self": 4.606263500045316, "children": { "TrainerController._reset_env": { "total": 8.100455400000001, "count": 1, "self": 4.326469600000003, "children": { "demo_to_buffer": { "total": 3.7739857999999984, "count": 2, "self": 0.00014229999999937348, "children": { "load_demonstration": { "total": 0.11465769999999953, "count": 2, "self": 0.11402429999999875, "children": { "read_file": { "total": 0.0006334000000007833, "count": 2, "self": 0.0006334000000007833 } } }, "make_demo_buffer": { "total": 3.6591857999999995, "count": 2, "self": 0.4698785999999968, "children": { "steps_from_proto": { "total": 3.1893072000000027, "count": 22656, "self": 1.668072100000022, "children": { "_process_rank_one_or_two_observation": { "total": 1.5212350999999806, "count": 135936, "self": 1.5212350999999806 } } } } } } } } }, "TrainerController.advance": { "total": 4442.913373099955, "count": 119060, "self": 1.3669635998958256, "children": { "env_step": { "total": 4441.546409500059, "count": 119060, "self": 3062.3130381001247, "children": { "SubprocessEnvManager._take_step": { "total": 1374.305394099931, "count": 1021026, "self": 40.6408524001622, "children": { "TorchPolicy.evaluate": { "total": 1333.6645416997687, "count": 1021026, "self": 1333.6645416997687 } } }, "workers": { "total": 4.9279773000030715, "count": 119060, "self": 0.0, "children": { "worker_root": { "total": 44429.99731309936, "count": 1021025, "is_parallel": true, "self": 42774.46296519929, "children": { "steps_from_proto": { "total": 0.004779600000000883, "count": 10, "is_parallel": true, "self": 0.0020871999999991786, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026924000000017045, "count": 60, "is_parallel": true, "self": 0.0026924000000017045 } } }, "UnityEnvironment.step": { "total": 1655.529568300074, "count": 1021025, "is_parallel": true, "self": 67.97142410005472, "children": { "UnityEnvironment._generate_step_input": { "total": 62.06028270020821, "count": 1021025, "is_parallel": true, "self": 62.06028270020821 }, "communicator.exchange": { "total": 1259.8166280997716, "count": 1021025, "is_parallel": true, "self": 1259.8166280997716 }, "steps_from_proto": { "total": 265.6812334000394, "count": 1021025, "is_parallel": true, "self": 131.21033820028225, "children": { "_process_rank_one_or_two_observation": { "total": 134.47089519975714, "count": 6126150, "is_parallel": true, "self": 134.47089519975714 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.2899999496294186e-05, "count": 1, "self": 3.2899999496294186e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4447.171796500018, "count": 34030, "is_parallel": true, "self": 2.0139200000476194, "children": { "process_trajectory": { "total": 542.5975950999762, "count": 34030, "is_parallel": true, "self": 542.0559983999763, "children": { "RLTrainer._checkpoint": { "total": 0.5415966999999569, "count": 10, "is_parallel": true, "self": 0.5415966999999569 } } }, "_update_policy": { "total": 3902.560281399994, "count": 488, "is_parallel": true, "self": 2934.9377803999914, "children": { "TorchPPOOptimizer.update": { "total": 967.6225010000028, "count": 152178, "is_parallel": true, "self": 967.6225010000028 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05470839999998134, "count": 1, "self": 0.010863599999538565, "children": { "RLTrainer._checkpoint": { "total": 0.043844800000442774, "count": 1, "self": 0.043844800000442774 } } } } } } }