{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4079792499542236, "min": 1.4079792499542236, "max": 1.4315000772476196, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68845.9609375, "min": 68845.9609375, "max": 77510.6640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.28288288288289, "min": 79.65161290322581, "max": 401.568, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49552.0, "min": 48842.0, "max": 50196.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999998.0, "min": 49923.0, "max": 1999998.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999998.0, "min": 49923.0, "max": 1999998.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.461583375930786, "min": 0.18043695390224457, "max": 2.4675095081329346, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1366.1788330078125, "min": 22.374181747436523, "max": 1479.01171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.846133812375971, "min": 1.7508931949494346, "max": 3.989339137222709, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2134.604265868664, "min": 217.1107561737299, "max": 2350.2620569467545, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.846133812375971, "min": 1.7508931949494346, "max": 3.989339137222709, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2134.604265868664, "min": 217.1107561737299, "max": 2350.2620569467545, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.020090855085355644, "min": 0.013503917881543101, "max": 0.020090855085355644, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.06027256525606693, "min": 0.029034888275297516, "max": 0.06027256525606693, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05240689453979333, "min": 0.020342164284860097, "max": 0.06511852579812209, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15722068361938, "min": 0.04068432856972019, "max": 0.19002282383541266, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.669998776699992e-06, "min": 3.669998776699992e-06, "max": 0.000295368001544, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1009996330099977e-05, "min": 1.1009996330099977e-05, "max": 0.0008442607685797501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012233, "min": 0.1012233, "max": 0.19845599999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036699, "min": 0.20758669999999996, "max": 0.5814202500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.104266999999989e-05, "min": 7.104266999999989e-05, "max": 0.0049229543999999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021312800999999964, "min": 0.00021312800999999964, "max": 0.014072870474999999, "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": "1694677749", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1694680299" }, "total": 2549.589513813, "count": 1, "self": 0.44119456299995363, "children": { "run_training.setup": { "total": 0.045548641999857864, "count": 1, "self": 0.045548641999857864 }, "TrainerController.start_learning": { "total": 2549.1027706080004, "count": 1, "self": 4.9132343669684815, "children": { "TrainerController._reset_env": { "total": 4.4795103260000815, "count": 1, "self": 4.4795103260000815 }, "TrainerController.advance": { "total": 2539.589244652031, "count": 232437, "self": 4.784930483128846, "children": { "env_step": { "total": 1966.3045730689694, "count": 232437, "self": 1663.3602848869305, "children": { "SubprocessEnvManager._take_step": { "total": 299.8340298119815, "count": 232437, "self": 17.150167089027036, "children": { "TorchPolicy.evaluate": { "total": 282.6838627229545, "count": 222870, "self": 282.6838627229545 } } }, "workers": { "total": 3.1102583700574087, "count": 232437, "self": 0.0, "children": { "worker_root": { "total": 2541.1361825189433, "count": 232437, "is_parallel": true, "self": 1182.9526100698981, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010172330000841612, "count": 1, "is_parallel": true, "self": 0.00025190100018335215, "children": { "_process_rank_one_or_two_observation": { "total": 0.000765331999900809, "count": 2, "is_parallel": true, "self": 0.000765331999900809 } } }, "UnityEnvironment.step": { "total": 0.0687924449998718, "count": 1, "is_parallel": true, "self": 0.00034733200004666287, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024011000004975358, "count": 1, "is_parallel": true, "self": 0.00024011000004975358 }, "communicator.exchange": { "total": 0.06721328999992693, "count": 1, "is_parallel": true, "self": 0.06721328999992693 }, "steps_from_proto": { "total": 0.0009917129998484597, "count": 1, "is_parallel": true, "self": 0.00022839400003249466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007633189998159651, "count": 2, "is_parallel": true, "self": 0.0007633189998159651 } } } } } } }, "UnityEnvironment.step": { "total": 1358.1835724490452, "count": 232436, "is_parallel": true, "self": 41.85366757796237, "children": { "UnityEnvironment._generate_step_input": { "total": 84.88742566097085, "count": 232436, "is_parallel": true, "self": 84.88742566097085 }, "communicator.exchange": { "total": 1128.1923159550213, "count": 232436, "is_parallel": true, "self": 1128.1923159550213 }, "steps_from_proto": { "total": 103.25016325509068, "count": 232436, "is_parallel": true, "self": 36.69019332018138, "children": { "_process_rank_one_or_two_observation": { "total": 66.5599699349093, "count": 464872, "is_parallel": true, "self": 66.5599699349093 } } } } } } } } } } }, "trainer_advance": { "total": 568.4997410999326, "count": 232437, "self": 7.195026745807354, "children": { "process_trajectory": { "total": 142.39084554112515, "count": 232437, "self": 141.11112964012636, "children": { "RLTrainer._checkpoint": { "total": 1.2797159009987809, "count": 10, "self": 1.2797159009987809 } } }, "_update_policy": { "total": 418.91386881300014, "count": 97, "self": 356.8973861159866, "children": { "TorchPPOOptimizer.update": { "total": 62.016482697013544, "count": 2910, "self": 62.016482697013544 } } } } } } }, "trainer_threads": { "total": 1.2280002010811586e-06, "count": 1, "self": 1.2280002010811586e-06 }, "TrainerController._save_models": { "total": 0.1207800350002799, "count": 1, "self": 0.0018727990004663297, "children": { "RLTrainer._checkpoint": { "total": 0.11890723599981357, "count": 1, "self": 0.11890723599981357 } } } } } } }