{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408982515335083, "min": 1.408982515335083, "max": 1.4270519018173218, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69581.1953125, "min": 68434.671875, "max": 78034.96875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.03030303030303, "min": 78.03030303030303, "max": 381.9541984732824, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48925.0, "min": 48793.0, "max": 50036.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999909.0, "min": 49937.0, "max": 1999909.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999909.0, "min": 49937.0, "max": 1999909.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4273247718811035, "min": 0.08055511116981506, "max": 2.4766767024993896, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1521.9326171875, "min": 10.472164154052734, "max": 1550.2744140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.692554573313091, "min": 1.8905668139457703, "max": 3.9651620964979846, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2315.231717467308, "min": 245.77368581295013, "max": 2478.9558626413345, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.692554573313091, "min": 1.8905668139457703, "max": 3.9651620964979846, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2315.231717467308, "min": 245.77368581295013, "max": 2478.9558626413345, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017290934980135515, "min": 0.013365351810676253, "max": 0.020027775602648033, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051872804940406546, "min": 0.028663894209603313, "max": 0.0589054299921069, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053598819093571774, "min": 0.020586885946492356, "max": 0.0619505880607499, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16079645728071532, "min": 0.04117377189298471, "max": 0.1858517641822497, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8068987310666662e-06, "min": 3.8068987310666662e-06, "max": 0.00029526562657812496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1420696193199999e-05, "min": 1.1420696193199999e-05, "max": 0.0008437870687376498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126893333333331, "min": 0.10126893333333331, "max": 0.19842187500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30380679999999993, "min": 0.20766889999999996, "max": 0.5812623500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.331977333333332e-05, "min": 7.331977333333332e-05, "max": 0.0049212515625, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021995931999999995, "min": 0.00021995931999999995, "max": 0.014064991265, "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": "1725808773", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725811208" }, "total": 2434.6200103409997, "count": 1, "self": 0.42744812399951115, "children": { "run_training.setup": { "total": 0.05004649400007111, "count": 1, "self": 0.05004649400007111 }, "TrainerController.start_learning": { "total": 2434.142515723, "count": 1, "self": 4.476379411911694, "children": { "TrainerController._reset_env": { "total": 1.947383797999919, "count": 1, "self": 1.947383797999919 }, "TrainerController.advance": { "total": 2427.6118514370883, "count": 233165, "self": 4.551914330011641, "children": { "env_step": { "total": 1913.4343108229368, "count": 233165, "self": 1510.1408784840019, "children": { "SubprocessEnvManager._take_step": { "total": 400.513320095019, "count": 233165, "self": 15.802166420860885, "children": { "TorchPolicy.evaluate": { "total": 384.71115367415814, "count": 222950, "self": 384.71115367415814 } } }, "workers": { "total": 2.780112243915937, "count": 233165, "self": 0.0, "children": { "worker_root": { "total": 2426.7088724471073, "count": 233165, "is_parallel": true, "self": 1204.0350078800325, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008515700001225923, "count": 1, "is_parallel": true, "self": 0.00025777600012588664, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005937939999967057, "count": 2, "is_parallel": true, "self": 0.0005937939999967057 } } }, "UnityEnvironment.step": { "total": 0.047169708000183164, "count": 1, "is_parallel": true, "self": 0.0003866920001200924, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019619900012912694, "count": 1, "is_parallel": true, "self": 0.00019619900012912694 }, "communicator.exchange": { "total": 0.045819342999948276, "count": 1, "is_parallel": true, "self": 0.045819342999948276 }, "steps_from_proto": { "total": 0.0007674739999856683, "count": 1, "is_parallel": true, "self": 0.00024249900025097304, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005249749997346953, "count": 2, "is_parallel": true, "self": 0.0005249749997346953 } } } } } } }, "UnityEnvironment.step": { "total": 1222.6738645670748, "count": 233164, "is_parallel": true, "self": 37.374036824006, "children": { "UnityEnvironment._generate_step_input": { "total": 78.52806145693148, "count": 233164, "is_parallel": true, "self": 78.52806145693148 }, "communicator.exchange": { "total": 1019.5272350390346, "count": 233164, "is_parallel": true, "self": 1019.5272350390346 }, "steps_from_proto": { "total": 87.24453124710271, "count": 233164, "is_parallel": true, "self": 31.052031407045433, "children": { "_process_rank_one_or_two_observation": { "total": 56.19249984005728, "count": 466328, "is_parallel": true, "self": 56.19249984005728 } } } } } } } } } } }, "trainer_advance": { "total": 509.6256262841398, "count": 233165, "self": 6.294125142221219, "children": { "process_trajectory": { "total": 162.40828790591877, "count": 233165, "self": 161.06025990291937, "children": { "RLTrainer._checkpoint": { "total": 1.3480280029993992, "count": 10, "self": 1.3480280029993992 } } }, "_update_policy": { "total": 340.9232132359998, "count": 97, "self": 274.6145122020057, "children": { "TorchPPOOptimizer.update": { "total": 66.30870103399411, "count": 2910, "self": 66.30870103399411 } } } } } } }, "trainer_threads": { "total": 1.0370004019932821e-06, "count": 1, "self": 1.0370004019932821e-06 }, "TrainerController._save_models": { "total": 0.10690003899981093, "count": 1, "self": 0.0024468259998684516, "children": { "RLTrainer._checkpoint": { "total": 0.10445321299994248, "count": 1, "self": 0.10445321299994248 } } } } } } }