{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405889868736267, "min": 1.405889868736267, "max": 1.4278374910354614, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69465.015625, "min": 69125.1640625, "max": 76329.359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 91.37707948243992, "min": 74.31372549019608, "max": 420.8235294117647, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49435.0, "min": 49270.0, "max": 50078.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999937.0, "min": 49800.0, "max": 1999937.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999937.0, "min": 49800.0, "max": 1999937.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4186506271362305, "min": -0.011333001777529716, "max": 2.5102219581604004, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1308.489990234375, "min": -1.3372942209243774, "max": 1596.5010986328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6697326011666527, "min": 1.6955916221742913, "max": 3.9706705316123236, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1985.3253372311592, "min": 200.07981141656637, "max": 2543.9238201379776, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6697326011666527, "min": 1.6955916221742913, "max": 3.9706705316123236, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1985.3253372311592, "min": 200.07981141656637, "max": 2543.9238201379776, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01784379117937836, "min": 0.013089904764152985, "max": 0.019333261817519085, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.053531373538135085, "min": 0.02617980952830597, "max": 0.057999785452557254, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05305976925624742, "min": 0.02305015977472067, "max": 0.06203926379481951, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15917930776874226, "min": 0.04610031954944134, "max": 0.17584166141847768, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8271487243166644e-06, "min": 3.8271487243166644e-06, "max": 0.0002953427265524251, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1481446172949993e-05, "min": 1.1481446172949993e-05, "max": 0.0008441496186167999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127568333333335, "min": 0.10127568333333335, "max": 0.198447575, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30382705000000004, "min": 0.20771485000000006, "max": 0.5813832000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.365659833333332e-05, "min": 7.365659833333332e-05, "max": 0.004922533992499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022096979499999995, "min": 0.00022096979499999995, "max": 0.014071021679999999, "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": "1743073649", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743076076" }, "total": 2427.4612823550005, "count": 1, "self": 0.49319613100124116, "children": { "run_training.setup": { "total": 0.027250359999925422, "count": 1, "self": 0.027250359999925422 }, "TrainerController.start_learning": { "total": 2426.9408358639994, "count": 1, "self": 4.298027413076852, "children": { "TrainerController._reset_env": { "total": 3.538413356999854, "count": 1, "self": 3.538413356999854 }, "TrainerController.advance": { "total": 2418.9820527769234, "count": 232900, "self": 4.384192232983878, "children": { "env_step": { "total": 1924.3131459919414, "count": 232900, "self": 1511.294237275953, "children": { "SubprocessEnvManager._take_step": { "total": 410.3535033229498, "count": 232900, "self": 15.525958743039837, "children": { "TorchPolicy.evaluate": { "total": 394.82754457990995, "count": 222934, "self": 394.82754457990995 } } }, "workers": { "total": 2.6654053930385544, "count": 232900, "self": 0.0, "children": { "worker_root": { "total": 2419.5208049901044, "count": 232900, "is_parallel": true, "self": 1183.5330577811444, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009204760001466639, "count": 1, "is_parallel": true, "self": 0.0002554810000674479, "children": { "_process_rank_one_or_two_observation": { "total": 0.000664995000079216, "count": 2, "is_parallel": true, "self": 0.000664995000079216 } } }, "UnityEnvironment.step": { "total": 0.031577791000017896, "count": 1, "is_parallel": true, "self": 0.0002779609997105581, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020176500015622878, "count": 1, "is_parallel": true, "self": 0.00020176500015622878 }, "communicator.exchange": { "total": 0.030240188000107082, "count": 1, "is_parallel": true, "self": 0.030240188000107082 }, "steps_from_proto": { "total": 0.0008578770000440272, "count": 1, "is_parallel": true, "self": 0.00022221000017452752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006356669998694997, "count": 2, "is_parallel": true, "self": 0.0006356669998694997 } } } } } } }, "UnityEnvironment.step": { "total": 1235.98774720896, "count": 232899, "is_parallel": true, "self": 36.28964931409496, "children": { "UnityEnvironment._generate_step_input": { "total": 82.11071454904959, "count": 232899, "is_parallel": true, "self": 82.11071454904959 }, "communicator.exchange": { "total": 1030.1250278428765, "count": 232899, "is_parallel": true, "self": 1030.1250278428765 }, "steps_from_proto": { "total": 87.46235550293886, "count": 232899, "is_parallel": true, "self": 32.573443801048825, "children": { "_process_rank_one_or_two_observation": { "total": 54.88891170189004, "count": 465798, "is_parallel": true, "self": 54.88891170189004 } } } } } } } } } } }, "trainer_advance": { "total": 490.2847145519979, "count": 232900, "self": 6.399858532017561, "children": { "process_trajectory": { "total": 164.8988035399791, "count": 232900, "self": 163.50283849097946, "children": { "RLTrainer._checkpoint": { "total": 1.395965048999642, "count": 10, "self": 1.395965048999642 } } }, "_update_policy": { "total": 318.98605248000126, "count": 97, "self": 252.86734888299202, "children": { "TorchPPOOptimizer.update": { "total": 66.11870359700924, "count": 2910, "self": 66.11870359700924 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.12234141699991596, "count": 1, "self": 0.0018569120002212003, "children": { "RLTrainer._checkpoint": { "total": 0.12048450499969476, "count": 1, "self": 0.12048450499969476 } } } } } } }