{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403333306312561, "min": 1.403333306312561, "max": 1.4281880855560303, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69004.703125, "min": 67695.3984375, "max": 79245.578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.03873239436619, "min": 83.35641891891892, "max": 391.65625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49438.0, "min": 48748.0, "max": 50135.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999912.0, "min": 49521.0, "max": 1999912.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999912.0, "min": 49521.0, "max": 1999912.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3431289196014404, "min": 0.2617979645729065, "max": 2.4934496879577637, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1330.897216796875, "min": 33.24834060668945, "max": 1421.86962890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5663751530605303, "min": 1.9371950784771461, "max": 3.903599581489824, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2025.7010869383812, "min": 246.02377496659756, "max": 2258.696846842766, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5663751530605303, "min": 1.9371950784771461, "max": 3.903599581489824, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2025.7010869383812, "min": 246.02377496659756, "max": 2258.696846842766, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.020381892008299474, "min": 0.013537094283189315, "max": 0.021864069072762504, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04076378401659895, "min": 0.02707418856637863, "max": 0.060084473738970696, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053280025037626425, "min": 0.019654034016033016, "max": 0.06093493960797786, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10656005007525285, "min": 0.03930806803206603, "max": 0.1828048188239336, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.6167984610999954e-06, "min": 4.6167984610999954e-06, "max": 0.00029535202654932494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.233596922199991e-06, "min": 9.233596922199991e-06, "max": 0.0008438692687102499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10153890000000002, "min": 0.10153890000000002, "max": 0.19845067499999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20307780000000003, "min": 0.20307780000000003, "max": 0.58128975, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.679110999999993e-05, "min": 8.679110999999993e-05, "max": 0.004922688682500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017358221999999986, "min": 0.00017358221999999986, "max": 0.014066358525000003, "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": "1695544909", "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": "1695547642" }, "total": 2732.75125987, "count": 1, "self": 0.7702364010001475, "children": { "run_training.setup": { "total": 0.04594907699998885, "count": 1, "self": 0.04594907699998885 }, "TrainerController.start_learning": { "total": 2731.935074392, "count": 1, "self": 5.265177794952706, "children": { "TrainerController._reset_env": { "total": 5.032021823999997, "count": 1, "self": 5.032021823999997 }, "TrainerController.advance": { "total": 2721.5008199170475, "count": 232471, "self": 5.246800760991846, "children": { "env_step": { "total": 2112.7445583790454, "count": 232471, "self": 1780.6811129280413, "children": { "SubprocessEnvManager._take_step": { "total": 328.568382215969, "count": 232471, "self": 18.812697165017653, "children": { "TorchPolicy.evaluate": { "total": 309.75568505095134, "count": 222926, "self": 309.75568505095134 } } }, "workers": { "total": 3.4950632350351896, "count": 232471, "self": 0.0, "children": { "worker_root": { "total": 2723.3210010020034, "count": 232471, "is_parallel": true, "self": 1268.6542476989475, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000981917000018484, "count": 1, "is_parallel": true, "self": 0.0002834150000126101, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006985020000058739, "count": 2, "is_parallel": true, "self": 0.0006985020000058739 } } }, "UnityEnvironment.step": { "total": 0.06995894499999622, "count": 1, "is_parallel": true, "self": 0.0003513890000022002, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023113800000373885, "count": 1, "is_parallel": true, "self": 0.00023113800000373885 }, "communicator.exchange": { "total": 0.06857375799998522, "count": 1, "is_parallel": true, "self": 0.06857375799998522 }, "steps_from_proto": { "total": 0.0008026600000050621, "count": 1, "is_parallel": true, "self": 0.00022248499999477644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005801750000102857, "count": 2, "is_parallel": true, "self": 0.0005801750000102857 } } } } } } }, "UnityEnvironment.step": { "total": 1454.6667533030559, "count": 232470, "is_parallel": true, "self": 44.69911095201883, "children": { "UnityEnvironment._generate_step_input": { "total": 88.15847285695375, "count": 232470, "is_parallel": true, "self": 88.15847285695375 }, "communicator.exchange": { "total": 1211.815813758052, "count": 232470, "is_parallel": true, "self": 1211.815813758052 }, "steps_from_proto": { "total": 109.9933557360313, "count": 232470, "is_parallel": true, "self": 38.44303494196572, "children": { "_process_rank_one_or_two_observation": { "total": 71.55032079406558, "count": 464940, "is_parallel": true, "self": 71.55032079406558 } } } } } } } } } } }, "trainer_advance": { "total": 603.50946077701, "count": 232471, "self": 7.969641397068017, "children": { "process_trajectory": { "total": 148.3959069229422, "count": 232471, "self": 146.98916987094256, "children": { "RLTrainer._checkpoint": { "total": 1.4067370519996416, "count": 10, "self": 1.4067370519996416 } } }, "_update_policy": { "total": 447.1439124569998, "count": 96, "self": 382.760180825995, "children": { "TorchPPOOptimizer.update": { "total": 64.38373163100476, "count": 2880, "self": 64.38373163100476 } } } } } } }, "trainer_threads": { "total": 1.1439997251727618e-06, "count": 1, "self": 1.1439997251727618e-06 }, "TrainerController._save_models": { "total": 0.1370537120001245, "count": 1, "self": 0.0021374380003180704, "children": { "RLTrainer._checkpoint": { "total": 0.13491627399980644, "count": 1, "self": 0.13491627399980644 } } } } } } }