{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4053606986999512, "min": 1.4053606986999512, "max": 1.4255105257034302, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70509.7578125, "min": 68182.71875, "max": 78667.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 108.4451754385965, "min": 76.31684698608964, "max": 381.47727272727275, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49451.0, "min": 48847.0, "max": 50355.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999897.0, "min": 49849.0, "max": 1999897.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999897.0, "min": 49849.0, "max": 1999897.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3696491718292236, "min": 0.08209816366434097, "max": 2.4646270275115967, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1080.56005859375, "min": 10.754859924316406, "max": 1561.366455078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5328398336443985, "min": 1.695553164445717, "max": 3.974897479330461, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1610.9749641418457, "min": 222.11746454238892, "max": 2455.429851949215, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5328398336443985, "min": 1.695553164445717, "max": 3.974897479330461, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1610.9749641418457, "min": 222.11746454238892, "max": 2455.429851949215, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01794922594999662, "min": 0.013998484487011511, "max": 0.021039786383820078, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05384767784998985, "min": 0.03081378785476166, "max": 0.06311935915146023, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049491981334156464, "min": 0.021841629253079496, "max": 0.05739608456691106, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14847594400246938, "min": 0.04368325850615899, "max": 0.1710285450021426, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.286298904600007e-06, "min": 3.286298904600007e-06, "max": 0.00029532202655932493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.85889671380002e-06, "min": 9.85889671380002e-06, "max": 0.0008439747186750998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1010954, "min": 0.1010954, "max": 0.198440675, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032862, "min": 0.20736904999999994, "max": 0.5813249, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.466046000000011e-05, "min": 6.466046000000011e-05, "max": 0.0049221896825, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019398138000000032, "min": 0.00019398138000000032, "max": 0.014068112510000001, "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": "1680970184", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680972615" }, "total": 2430.9197570300003, "count": 1, "self": 0.7413433420001638, "children": { "run_training.setup": { "total": 0.11074354699997002, "count": 1, "self": 0.11074354699997002 }, "TrainerController.start_learning": { "total": 2430.0676701410002, "count": 1, "self": 4.4772201469586435, "children": { "TrainerController._reset_env": { "total": 3.9968345260000433, "count": 1, "self": 3.9968345260000433 }, "TrainerController.advance": { "total": 2421.3920585740416, "count": 232593, "self": 4.941469256021264, "children": { "env_step": { "total": 1904.4902522670131, "count": 232593, "self": 1614.796305447047, "children": { "SubprocessEnvManager._take_step": { "total": 286.70980720705234, "count": 232593, "self": 17.643615697113432, "children": { "TorchPolicy.evaluate": { "total": 269.0661915099389, "count": 223037, "self": 269.0661915099389 } } }, "workers": { "total": 2.9841396129137365, "count": 232593, "self": 0.0, "children": { "worker_root": { "total": 2421.672096019928, "count": 232593, "is_parallel": true, "self": 1102.6373573968544, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009648889999880339, "count": 1, "is_parallel": true, "self": 0.00027333000002727204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006915589999607619, "count": 2, "is_parallel": true, "self": 0.0006915589999607619 } } }, "UnityEnvironment.step": { "total": 0.036444650000021284, "count": 1, "is_parallel": true, "self": 0.00033982600018589437, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024193799993099674, "count": 1, "is_parallel": true, "self": 0.00024193799993099674 }, "communicator.exchange": { "total": 0.03504486499991799, "count": 1, "is_parallel": true, "self": 0.03504486499991799 }, "steps_from_proto": { "total": 0.0008180209999864019, "count": 1, "is_parallel": true, "self": 0.00022097399994436273, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005970470000420391, "count": 2, "is_parallel": true, "self": 0.0005970470000420391 } } } } } } }, "UnityEnvironment.step": { "total": 1319.0347386230737, "count": 232592, "is_parallel": true, "self": 38.80159185099478, "children": { "UnityEnvironment._generate_step_input": { "total": 85.45931436394528, "count": 232592, "is_parallel": true, "self": 85.45931436394528 }, "communicator.exchange": { "total": 1101.112656385104, "count": 232592, "is_parallel": true, "self": 1101.112656385104 }, "steps_from_proto": { "total": 93.66117602302961, "count": 232592, "is_parallel": true, "self": 37.69708416409833, "children": { "_process_rank_one_or_two_observation": { "total": 55.96409185893128, "count": 465184, "is_parallel": true, "self": 55.96409185893128 } } } } } } } } } } }, "trainer_advance": { "total": 511.96033705100706, "count": 232593, "self": 6.811585958118826, "children": { "process_trajectory": { "total": 139.3068606008859, "count": 232593, "self": 138.05018583688616, "children": { "RLTrainer._checkpoint": { "total": 1.2566747639997402, "count": 8, "self": 1.2566747639997402 } } }, "_update_policy": { "total": 365.84189049200234, "count": 97, "self": 307.80789676399763, "children": { "TorchPPOOptimizer.update": { "total": 58.0339937280047, "count": 2910, "self": 58.0339937280047 } } } } } } }, "trainer_threads": { "total": 1.5410000742122065e-06, "count": 1, "self": 1.5410000742122065e-06 }, "TrainerController._save_models": { "total": 0.20155535300000338, "count": 1, "self": 0.0031017239998618606, "children": { "RLTrainer._checkpoint": { "total": 0.19845362900014152, "count": 1, "self": 0.19845362900014152 } } } } } } }