{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3962702751159668, "min": 1.3962702751159668, "max": 1.3979963064193726, "count": 10 }, "Huggy.Policy.Entropy.sum": { "value": 70525.609375, "min": 10406.6845703125, "max": 70757.2421875, "count": 10 }, "Huggy.Environment.EpisodeLength.mean": { "value": 69.4281690140845, "min": 64.24038461538461, "max": 73.94602698650675, "count": 10 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49294.0, "min": 6681.0, "max": 49402.0, "count": 10 }, "Huggy.Step.mean": { "value": 1999937.0, "min": 1549924.0, "max": 1999937.0, "count": 10 }, "Huggy.Step.sum": { "value": 1999937.0, "min": 1549924.0, "max": 1999937.0, "count": 10 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.515529155731201, "min": 2.411447286605835, "max": 2.5417237281799316, "count": 10 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1786.025634765625, "min": 248.3790740966797, "max": 1823.8685302734375, "count": 10 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8766558966166538, "min": 3.601232999736823, "max": 4.003352481117849, "count": 10 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2752.425686597824, "min": 370.92699897289276, "max": 2867.489096879959, "count": 10 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8766558966166538, "min": 3.601232999736823, "max": 4.003352481117849, "count": 10 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2752.425686597824, "min": 370.92699897289276, "max": 2867.489096879959, "count": 10 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01654704478266164, "min": 0.012674073890472452, "max": 0.01862188071229159, "count": 9 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04964113434798492, "min": 0.025348147780944904, "max": 0.05586564213687477, "count": 9 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.059121200690666835, "min": 0.05479614759484927, "max": 0.05958442048480113, "count": 9 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1773636020720005, "min": 0.10959229518969854, "max": 0.1773636020720005, "count": 9 }, "Huggy.Policy.LearningRate.mean": { "value": 3.805748731450005e-06, "min": 3.805748731450005e-06, "max": 6.389302870234997e-05, "count": 9 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1417246194350015e-05, "min": 1.1417246194350015e-05, "max": 0.00016858089380645, "count": 9 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126855000000001, "min": 0.10126855000000001, "max": 0.12129765, "count": 9 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30380565000000004, "min": 0.20766364999999998, "max": 0.35619354999999997, "count": 9 }, "Huggy.Policy.Beta.mean": { "value": 7.330064500000009e-05, "min": 7.330064500000009e-05, "max": 0.0010727527349999998, "count": 9 }, "Huggy.Policy.Beta.sum": { "value": 0.00021990193500000027, "min": 0.00021990193500000027, "max": 0.002834058145000001, "count": 9 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687529002", "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 --resume", "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": "1687529606" }, "total": 603.6727417490001, "count": 1, "self": 0.4745919599999979, "children": { "run_training.setup": { "total": 0.049950250999700074, "count": 1, "self": 0.049950250999700074 }, "TrainerController.start_learning": { "total": 603.1481995380004, "count": 1, "self": 1.1066538340346597, "children": { "TrainerController._reset_env": { "total": 5.402094428000055, "count": 1, "self": 5.402094428000055 }, "TrainerController.advance": { "total": 596.5156057699655, "count": 54119, "self": 1.142112884058406, "children": { "env_step": { "total": 468.21008696191075, "count": 54119, "self": 396.26244911695403, "children": { "SubprocessEnvManager._take_step": { "total": 71.27073576100292, "count": 54119, "self": 4.060325537970584, "children": { "TorchPolicy.evaluate": { "total": 67.21041022303234, "count": 51059, "self": 67.21041022303234 } } }, "workers": { "total": 0.6769020839537916, "count": 54119, "self": 0.0, "children": { "worker_root": { "total": 601.10078750396, "count": 54119, "is_parallel": true, "self": 276.3752652009939, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009561619999658433, "count": 1, "is_parallel": true, "self": 0.00030014200001460267, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006560199999512406, "count": 2, "is_parallel": true, "self": 0.0006560199999512406 } } }, "UnityEnvironment.step": { "total": 0.031266926000171225, "count": 1, "is_parallel": true, "self": 0.0003033080006389355, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022445099966716953, "count": 1, "is_parallel": true, "self": 0.00022445099966716953 }, "communicator.exchange": { "total": 0.030025241000203096, "count": 1, "is_parallel": true, "self": 0.030025241000203096 }, "steps_from_proto": { "total": 0.000713925999662024, "count": 1, "is_parallel": true, "self": 0.0002217610003754089, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004921649992866151, "count": 2, "is_parallel": true, "self": 0.0004921649992866151 } } } } } } }, "UnityEnvironment.step": { "total": 324.72552230296606, "count": 54118, "is_parallel": true, "self": 9.33465459189847, "children": { "UnityEnvironment._generate_step_input": { "total": 19.860394424959395, "count": 54118, "is_parallel": true, "self": 19.860394424959395 }, "communicator.exchange": { "total": 272.06546121700376, "count": 54118, "is_parallel": true, "self": 272.06546121700376 }, "steps_from_proto": { "total": 23.465012069104432, "count": 54118, "is_parallel": true, "self": 9.009660344163422, "children": { "_process_rank_one_or_two_observation": { "total": 14.45535172494101, "count": 108236, "is_parallel": true, "self": 14.45535172494101 } } } } } } } } } } }, "trainer_advance": { "total": 127.16340592399638, "count": 54119, "self": 1.5986960758796158, "children": { "process_trajectory": { "total": 38.54078687411584, "count": 54119, "self": 38.39439565911562, "children": { "RLTrainer._checkpoint": { "total": 0.14639121500022156, "count": 1, "self": 0.14639121500022156 } } }, "_update_policy": { "total": 87.02392297400093, "count": 22, "self": 73.55606760300589, "children": { "TorchPPOOptimizer.update": { "total": 13.46785537099504, "count": 660, "self": 13.46785537099504 } } } } } } }, "trainer_threads": { "total": 1.6220001270994544e-06, "count": 1, "self": 1.6220001270994544e-06 }, "TrainerController._save_models": { "total": 0.12384388400005264, "count": 1, "self": 0.0023005259999990813, "children": { "RLTrainer._checkpoint": { "total": 0.12154335800005356, "count": 1, "self": 0.12154335800005356 } } } } } } }