{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402205228805542, "min": 1.402205228805542, "max": 1.426506757736206, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70289.7421875, "min": 69166.9609375, "max": 77072.84375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.95894909688013, "min": 80.22764227642277, "max": 384.9153846153846, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49304.0, "min": 48866.0, "max": 50108.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999951.0, "min": 49717.0, "max": 1999951.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999951.0, "min": 49717.0, "max": 1999951.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.46866512298584, "min": 0.08215023577213287, "max": 2.493443250656128, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1503.4169921875, "min": 10.597380638122559, "max": 1503.4169921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7829865467763693, "min": 2.0338714774264846, "max": 4.066064072489739, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2303.838806986809, "min": 262.3694205880165, "max": 2369.8820927739143, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7829865467763693, "min": 2.0338714774264846, "max": 4.066064072489739, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2303.838806986809, "min": 262.3694205880165, "max": 2369.8820927739143, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019765743900724272, "min": 0.013843088384601288, "max": 0.019765743900724272, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05929723170217282, "min": 0.027686176769202576, "max": 0.05929723170217282, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057087204812301534, "min": 0.0240795914704601, "max": 0.060657571504513424, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1712616144369046, "min": 0.0481591829409202, "max": 0.1758168764412403, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.619948793383334e-06, "min": 3.619948793383334e-06, "max": 0.00029534205155264993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0859846380150003e-05, "min": 1.0859846380150003e-05, "max": 0.000844266018578, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120661666666665, "min": 0.10120661666666665, "max": 0.19844735, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30361984999999997, "min": 0.20755615000000005, "max": 0.5814220000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.02101716666667e-05, "min": 7.02101716666667e-05, "max": 0.004922522765000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021063051500000012, "min": 0.00021063051500000012, "max": 0.014072957800000003, "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": "1688970269", "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", "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": "1688972584" }, "total": 2315.505838022, "count": 1, "self": 0.44061305400009587, "children": { "run_training.setup": { "total": 0.04628638399992724, "count": 1, "self": 0.04628638399992724 }, "TrainerController.start_learning": { "total": 2315.018938584, "count": 1, "self": 4.2046122029978505, "children": { "TrainerController._reset_env": { "total": 4.187538060000065, "count": 1, "self": 4.187538060000065 }, "TrainerController.advance": { "total": 2306.508130236002, "count": 232653, "self": 4.336184311830948, "children": { "env_step": { "total": 1787.482703128982, "count": 232653, "self": 1505.48554131493, "children": { "SubprocessEnvManager._take_step": { "total": 279.3201724170326, "count": 232653, "self": 16.01784881513845, "children": { "TorchPolicy.evaluate": { "total": 263.30232360189416, "count": 222983, "self": 263.30232360189416 } } }, "workers": { "total": 2.6769893970192697, "count": 232653, "self": 0.0, "children": { "worker_root": { "total": 2307.464894696004, "count": 232653, "is_parallel": true, "self": 1078.8940949509738, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009150519999820972, "count": 1, "is_parallel": true, "self": 0.00023982499988051131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006752270001015859, "count": 2, "is_parallel": true, "self": 0.0006752270001015859 } } }, "UnityEnvironment.step": { "total": 0.04712010100001862, "count": 1, "is_parallel": true, "self": 0.0003886160001229655, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023722899993572355, "count": 1, "is_parallel": true, "self": 0.00023722899993572355 }, "communicator.exchange": { "total": 0.045743552999965686, "count": 1, "is_parallel": true, "self": 0.045743552999965686 }, "steps_from_proto": { "total": 0.0007507029999942461, "count": 1, "is_parallel": true, "self": 0.00022274100001595798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005279619999782881, "count": 2, "is_parallel": true, "self": 0.0005279619999782881 } } } } } } }, "UnityEnvironment.step": { "total": 1228.5707997450304, "count": 232652, "is_parallel": true, "self": 38.94564535214408, "children": { "UnityEnvironment._generate_step_input": { "total": 77.509704132906, "count": 232652, "is_parallel": true, "self": 77.509704132906 }, "communicator.exchange": { "total": 1017.1591010549233, "count": 232652, "is_parallel": true, "self": 1017.1591010549233 }, "steps_from_proto": { "total": 94.956349205057, "count": 232652, "is_parallel": true, "self": 33.351332181047724, "children": { "_process_rank_one_or_two_observation": { "total": 61.60501702400927, "count": 465304, "is_parallel": true, "self": 61.60501702400927 } } } } } } } } } } }, "trainer_advance": { "total": 514.6892427951891, "count": 232653, "self": 6.590821672150241, "children": { "process_trajectory": { "total": 132.5832292460392, "count": 232653, "self": 131.17098568403958, "children": { "RLTrainer._checkpoint": { "total": 1.4122435619996168, "count": 10, "self": 1.4122435619996168 } } }, "_update_policy": { "total": 375.51519187699967, "count": 97, "self": 316.0227749099971, "children": { "TorchPPOOptimizer.update": { "total": 59.492416967002555, "count": 2910, "self": 59.492416967002555 } } } } } } }, "trainer_threads": { "total": 1.0399999155197293e-06, "count": 1, "self": 1.0399999155197293e-06 }, "TrainerController._save_models": { "total": 0.11865704499996355, "count": 1, "self": 0.0018862309998439741, "children": { "RLTrainer._checkpoint": { "total": 0.11677081400011957, "count": 1, "self": 0.11677081400011957 } } } } } } }