{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.410196304321289, "min": 1.410196304321289, "max": 1.4282119274139404, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70327.8984375, "min": 69285.09375, "max": 77354.8984375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.57531760435572, "min": 80.24675324675324, "max": 385.24615384615385, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49356.0, "min": 49214.0, "max": 50082.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49561.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49561.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3875792026519775, "min": 0.1267990618944168, "max": 2.466287612915039, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1315.55615234375, "min": 16.357078552246094, "max": 1453.3931884765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6999197679076565, "min": 1.8566290491311126, "max": 4.016564288073116, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2038.6557921171188, "min": 239.5051473379135, "max": 2319.503956437111, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6999197679076565, "min": 1.8566290491311126, "max": 4.016564288073116, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2038.6557921171188, "min": 239.5051473379135, "max": 2319.503956437111, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016785664005308513, "min": 0.013990444232735577, "max": 0.020199262915088587, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05035699201592554, "min": 0.030843315727543084, "max": 0.060597788745265765, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0541473965264029, "min": 0.022702645417302846, "max": 0.06311731984217962, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1624421895792087, "min": 0.04540529083460569, "max": 0.18935195952653885, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.458398847233325e-06, "min": 3.458398847233325e-06, "max": 0.000295292626569125, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0375196541699975e-05, "min": 1.0375196541699975e-05, "max": 0.00084404266865245, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115276666666667, "min": 0.10115276666666667, "max": 0.198430875, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034583, "min": 0.20750065, "max": 0.58134755, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.752305666666654e-05, "min": 6.752305666666654e-05, "max": 0.0049217006625, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002025691699999996, "min": 0.0002025691699999996, "max": 0.014069242745000004, "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": "1702661456", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702663990" }, "total": 2534.074081449, "count": 1, "self": 0.44371237600034874, "children": { "run_training.setup": { "total": 0.05114397199997711, "count": 1, "self": 0.05114397199997711 }, "TrainerController.start_learning": { "total": 2533.579225101, "count": 1, "self": 4.667168503018729, "children": { "TrainerController._reset_env": { "total": 3.2252808480000112, "count": 1, "self": 3.2252808480000112 }, "TrainerController.advance": { "total": 2525.578315334981, "count": 232573, "self": 4.894461345959371, "children": { "env_step": { "total": 2011.6513324879822, "count": 232573, "self": 1667.896120232203, "children": { "SubprocessEnvManager._take_step": { "total": 340.7415618619277, "count": 232573, "self": 17.561886632799883, "children": { "TorchPolicy.evaluate": { "total": 323.17967522912784, "count": 222953, "self": 323.17967522912784 } } }, "workers": { "total": 3.0136503938516626, "count": 232573, "self": 0.0, "children": { "worker_root": { "total": 2525.8722689128936, "count": 232573, "is_parallel": true, "self": 1173.2819196747398, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006747250000671556, "count": 1, "is_parallel": true, "self": 0.00023102800003016455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004436970000369911, "count": 2, "is_parallel": true, "self": 0.0004436970000369911 } } }, "UnityEnvironment.step": { "total": 0.03130676700004642, "count": 1, "is_parallel": true, "self": 0.000336960000140607, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002450849999604543, "count": 1, "is_parallel": true, "self": 0.0002450849999604543 }, "communicator.exchange": { "total": 0.029994890000011765, "count": 1, "is_parallel": true, "self": 0.029994890000011765 }, "steps_from_proto": { "total": 0.0007298319999335945, "count": 1, "is_parallel": true, "self": 0.00021907600000758976, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005107559999260047, "count": 2, "is_parallel": true, "self": 0.0005107559999260047 } } } } } } }, "UnityEnvironment.step": { "total": 1352.5903492381537, "count": 232572, "is_parallel": true, "self": 41.8287449781933, "children": { "UnityEnvironment._generate_step_input": { "total": 87.20865759001504, "count": 232572, "is_parallel": true, "self": 87.20865759001504 }, "communicator.exchange": { "total": 1129.4069545109764, "count": 232572, "is_parallel": true, "self": 1129.4069545109764 }, "steps_from_proto": { "total": 94.14599215896897, "count": 232572, "is_parallel": true, "self": 34.97826694000935, "children": { "_process_rank_one_or_two_observation": { "total": 59.16772521895962, "count": 465144, "is_parallel": true, "self": 59.16772521895962 } } } } } } } } } } }, "trainer_advance": { "total": 509.0325215010396, "count": 232573, "self": 7.196402642107273, "children": { "process_trajectory": { "total": 163.62892595493497, "count": 232573, "self": 162.36331379493538, "children": { "RLTrainer._checkpoint": { "total": 1.2656121599995913, "count": 10, "self": 1.2656121599995913 } } }, "_update_policy": { "total": 338.20719290399734, "count": 97, "self": 273.32955850599956, "children": { "TorchPPOOptimizer.update": { "total": 64.87763439799778, "count": 2910, "self": 64.87763439799778 } } } } } } }, "trainer_threads": { "total": 1.0150001799047459e-06, "count": 1, "self": 1.0150001799047459e-06 }, "TrainerController._save_models": { "total": 0.1084593999999015, "count": 1, "self": 0.001878084000054514, "children": { "RLTrainer._checkpoint": { "total": 0.10658131599984699, "count": 1, "self": 0.10658131599984699 } } } } } } }