{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4046602249145508, "min": 1.4046602249145508, "max": 1.4261837005615234, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69315.765625, "min": 68510.109375, "max": 75755.1484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.04411764705883, "min": 83.42398648648648, "max": 441.6725663716814, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49528.0, "min": 48818.0, "max": 50184.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999327.0, "min": 49301.0, "max": 1999327.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999327.0, "min": 49301.0, "max": 1999327.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4544150829315186, "min": 0.07299845665693283, "max": 2.4544150829315186, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1335.2017822265625, "min": 8.175827026367188, "max": 1440.407470703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.838484943351325, "min": 1.8315338071967875, "max": 3.9022472385593034, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2088.1358091831207, "min": 205.1317864060402, "max": 2229.694820046425, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.838484943351325, "min": 1.8315338071967875, "max": 3.9022472385593034, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2088.1358091831207, "min": 205.1317864060402, "max": 2229.694820046425, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01648666559841432, "min": 0.01234751154309682, "max": 0.02011386437886055, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04945999679524296, "min": 0.02469502308619364, "max": 0.05573470930976328, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05659332511325677, "min": 0.020694879504541554, "max": 0.057292325608432296, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16977997533977032, "min": 0.04138975900908311, "max": 0.16977997533977032, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2661989113000044e-06, "min": 3.2661989113000044e-06, "max": 0.00029532502655832497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.798596733900014e-06, "min": 9.798596733900014e-06, "max": 0.00084391546869485, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108870000000003, "min": 0.10108870000000003, "max": 0.19844167500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032661000000001, "min": 0.20733314999999997, "max": 0.5813051500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.43261300000001e-05, "min": 6.43261300000001e-05, "max": 0.004922239582500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001929783900000003, "min": 0.0001929783900000003, "max": 0.014067126985, "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": "1686496487", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1686498876" }, "total": 2388.610088746, "count": 1, "self": 0.44945959200003927, "children": { "run_training.setup": { "total": 0.04296996200002923, "count": 1, "self": 0.04296996200002923 }, "TrainerController.start_learning": { "total": 2388.1176591920002, "count": 1, "self": 4.350188804093705, "children": { "TrainerController._reset_env": { "total": 4.2302159700000175, "count": 1, "self": 4.2302159700000175 }, "TrainerController.advance": { "total": 2379.420209664906, "count": 232271, "self": 4.516355239888981, "children": { "env_step": { "total": 1855.4494778699259, "count": 232271, "self": 1560.481497130054, "children": { "SubprocessEnvManager._take_step": { "total": 292.20921556096016, "count": 232271, "self": 16.4780761729412, "children": { "TorchPolicy.evaluate": { "total": 275.73113938801896, "count": 222898, "self": 275.73113938801896 } } }, "workers": { "total": 2.7587651789116876, "count": 232271, "self": 0.0, "children": { "worker_root": { "total": 2380.6334304179654, "count": 232271, "is_parallel": true, "self": 1106.5844975288803, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009165630000325109, "count": 1, "is_parallel": true, "self": 0.000255814000013288, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006607490000192229, "count": 2, "is_parallel": true, "self": 0.0006607490000192229 } } }, "UnityEnvironment.step": { "total": 0.029288724000025468, "count": 1, "is_parallel": true, "self": 0.0003116160000899981, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021070899998676396, "count": 1, "is_parallel": true, "self": 0.00021070899998676396 }, "communicator.exchange": { "total": 0.027944496999964485, "count": 1, "is_parallel": true, "self": 0.027944496999964485 }, "steps_from_proto": { "total": 0.0008219019999842203, "count": 1, "is_parallel": true, "self": 0.00021684099993990458, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006050610000443157, "count": 2, "is_parallel": true, "self": 0.0006050610000443157 } } } } } } }, "UnityEnvironment.step": { "total": 1274.048932889085, "count": 232270, "is_parallel": true, "self": 38.65216903301075, "children": { "UnityEnvironment._generate_step_input": { "total": 78.35512559497914, "count": 232270, "is_parallel": true, "self": 78.35512559497914 }, "communicator.exchange": { "total": 1063.355596394007, "count": 232270, "is_parallel": true, "self": 1063.355596394007 }, "steps_from_proto": { "total": 93.68604186708819, "count": 232270, "is_parallel": true, "self": 33.28071472624583, "children": { "_process_rank_one_or_two_observation": { "total": 60.40532714084236, "count": 464540, "is_parallel": true, "self": 60.40532714084236 } } } } } } } } } } }, "trainer_advance": { "total": 519.4543765550912, "count": 232271, "self": 6.461405668073553, "children": { "process_trajectory": { "total": 133.50865123701698, "count": 232271, "self": 132.13062721401747, "children": { "RLTrainer._checkpoint": { "total": 1.3780240229995115, "count": 10, "self": 1.3780240229995115 } } }, "_update_policy": { "total": 379.48431965000077, "count": 97, "self": 318.8344688569891, "children": { "TorchPPOOptimizer.update": { "total": 60.649850793011694, "count": 2910, "self": 60.649850793011694 } } } } } } }, "trainer_threads": { "total": 1.0030003068095539e-06, "count": 1, "self": 1.0030003068095539e-06 }, "TrainerController._save_models": { "total": 0.11704374999999345, "count": 1, "self": 0.0018557080002210569, "children": { "RLTrainer._checkpoint": { "total": 0.1151880419997724, "count": 1, "self": 0.1151880419997724 } } } } } } }