{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4094890356063843, "min": 1.4094890356063843, "max": 1.4298068284988403, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69072.0078125, "min": 66653.671875, "max": 78590.7265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.21514629948365, "min": 74.50604229607251, "max": 411.1967213114754, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49510.0, "min": 49236.0, "max": 50234.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999994.0, "min": 49796.0, "max": 1999994.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999994.0, "min": 49796.0, "max": 1999994.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5138745307922363, "min": 0.10167175531387329, "max": 2.5484540462493896, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1460.56103515625, "min": 12.810641288757324, "max": 1621.6719970703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9396596900772516, "min": 1.7639555815193388, "max": 3.990983657955383, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2288.942279934883, "min": 222.2584032714367, "max": 2570.1934757232666, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9396596900772516, "min": 1.7639555815193388, "max": 3.990983657955383, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2288.942279934883, "min": 222.2584032714367, "max": 2570.1934757232666, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018320147966733202, "min": 0.012767271964306322, "max": 0.020117738543194718, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05496044390019961, "min": 0.025534543928612645, "max": 0.058295216174641, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05907784787317117, "min": 0.020861170161515473, "max": 0.063293013907969, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17723354361951352, "min": 0.041722340323030946, "max": 0.18038403888543447, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.80224873261666e-06, "min": 3.80224873261666e-06, "max": 0.00029536222654592495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1406746197849979e-05, "min": 1.1406746197849979e-05, "max": 0.00084425506858165, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126738333333334, "min": 0.10126738333333334, "max": 0.198454075, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30380215, "min": 0.20766690000000004, "max": 0.5814183499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.324242833333324e-05, "min": 7.324242833333324e-05, "max": 0.004922858342500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021972728499999972, "min": 0.00021972728499999972, "max": 0.014072775664999999, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699533646", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699536051" }, "total": 2405.138778345, "count": 1, "self": 0.4386388419998184, "children": { "run_training.setup": { "total": 0.04562780300000213, "count": 1, "self": 0.04562780300000213 }, "TrainerController.start_learning": { "total": 2404.6545117, "count": 1, "self": 4.512966579038675, "children": { "TrainerController._reset_env": { "total": 8.83682247400003, "count": 1, "self": 8.83682247400003 }, "TrainerController.advance": { "total": 2391.205839951961, "count": 233223, "self": 4.579203865867839, "children": { "env_step": { "total": 1887.9817203360371, "count": 233223, "self": 1550.0304816811256, "children": { "SubprocessEnvManager._take_step": { "total": 335.14308387701817, "count": 233223, "self": 16.06458660413307, "children": { "TorchPolicy.evaluate": { "total": 319.0784972728851, "count": 222917, "self": 319.0784972728851 } } }, "workers": { "total": 2.808154777893378, "count": 233223, "self": 0.0, "children": { "worker_root": { "total": 2397.491178723017, "count": 233223, "is_parallel": true, "self": 1130.759706687989, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009285439999757727, "count": 1, "is_parallel": true, "self": 0.0002545720000171059, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006739719999586669, "count": 2, "is_parallel": true, "self": 0.0006739719999586669 } } }, "UnityEnvironment.step": { "total": 0.031415774999970836, "count": 1, "is_parallel": true, "self": 0.00032431999994742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002159349999715232, "count": 1, "is_parallel": true, "self": 0.0002159349999715232 }, "communicator.exchange": { "total": 0.030104072000028737, "count": 1, "is_parallel": true, "self": 0.030104072000028737 }, "steps_from_proto": { "total": 0.0007714480000231561, "count": 1, "is_parallel": true, "self": 0.0001874099999668033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005840380000563528, "count": 2, "is_parallel": true, "self": 0.0005840380000563528 } } } } } } }, "UnityEnvironment.step": { "total": 1266.7314720350282, "count": 233222, "is_parallel": true, "self": 40.19105119712731, "children": { "UnityEnvironment._generate_step_input": { "total": 83.5423120270155, "count": 233222, "is_parallel": true, "self": 83.5423120270155 }, "communicator.exchange": { "total": 1052.3745644529936, "count": 233222, "is_parallel": true, "self": 1052.3745644529936 }, "steps_from_proto": { "total": 90.62354435789189, "count": 233222, "is_parallel": true, "self": 31.66564899887868, "children": { "_process_rank_one_or_two_observation": { "total": 58.95789535901321, "count": 466444, "is_parallel": true, "self": 58.95789535901321 } } } } } } } } } } }, "trainer_advance": { "total": 498.64491575005593, "count": 233223, "self": 6.572839714962754, "children": { "process_trajectory": { "total": 153.73095379709383, "count": 233223, "self": 152.57438877409407, "children": { "RLTrainer._checkpoint": { "total": 1.1565650229997573, "count": 10, "self": 1.1565650229997573 } } }, "_update_policy": { "total": 338.34112223799934, "count": 97, "self": 276.0799109579974, "children": { "TorchPPOOptimizer.update": { "total": 62.26121128000193, "count": 2910, "self": 62.26121128000193 } } } } } } }, "trainer_threads": { "total": 1.1310003174003214e-06, "count": 1, "self": 1.1310003174003214e-06 }, "TrainerController._save_models": { "total": 0.09888156399983927, "count": 1, "self": 0.0019033590001527045, "children": { "RLTrainer._checkpoint": { "total": 0.09697820499968657, "count": 1, "self": 0.09697820499968657 } } } } } } }