{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.406259536743164, "min": 1.406259536743164, "max": 1.4298001527786255, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71070.953125, "min": 67192.6875, "max": 79608.1015625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.8375, "min": 88.34280639431617, "max": 375.187969924812, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49842.0, "min": 49164.0, "max": 49921.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999607.0, "min": 49550.0, "max": 1999607.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999607.0, "min": 49550.0, "max": 1999607.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3261377811431885, "min": 0.13574489951133728, "max": 2.423707962036133, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1116.546142578125, "min": 17.91832733154297, "max": 1323.3446044921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.533173110584418, "min": 1.7383253865621306, "max": 3.888927292268715, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1695.9230930805206, "min": 229.45895102620125, "max": 2078.0930726528168, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.533173110584418, "min": 1.7383253865621306, "max": 3.888927292268715, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1695.9230930805206, "min": 229.45895102620125, "max": 2078.0930726528168, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018315091429232985, "min": 0.013727532109805906, "max": 0.019239620664787557, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05494527428769895, "min": 0.027455064219611813, "max": 0.055743372597741356, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05122981969681051, "min": 0.02188951565573613, "max": 0.061367499207456905, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15368945909043152, "min": 0.04377903131147226, "max": 0.18410249762237071, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.266798911099999e-06, "min": 3.266798911099999e-06, "max": 0.00029532330155890003, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.800396733299998e-06, "min": 9.800396733299998e-06, "max": 0.0008442393185868998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108889999999998, "min": 0.10108889999999998, "max": 0.19844109999999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30326669999999994, "min": 0.20730525000000005, "max": 0.5814131, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.433611000000002e-05, "min": 6.433611000000002e-05, "max": 0.0049222108900000006, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019300833000000006, "min": 0.00019300833000000006, "max": 0.01407251369, "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": "1695208371", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1695210874" }, "total": 2502.8018295439997, "count": 1, "self": 0.44234815999971033, "children": { "run_training.setup": { "total": 0.06566901500002587, "count": 1, "self": 0.06566901500002587 }, "TrainerController.start_learning": { "total": 2502.293812369, "count": 1, "self": 4.500375942912797, "children": { "TrainerController._reset_env": { "total": 4.996839191000049, "count": 1, "self": 4.996839191000049 }, "TrainerController.advance": { "total": 2492.669523439087, "count": 231790, "self": 4.620009810227202, "children": { "env_step": { "total": 1926.7616455069883, "count": 231790, "self": 1625.3007979190234, "children": { "SubprocessEnvManager._take_step": { "total": 298.43505598696686, "count": 231790, "self": 16.545508152974207, "children": { "TorchPolicy.evaluate": { "total": 281.88954783399265, "count": 222980, "self": 281.88954783399265 } } }, "workers": { "total": 3.025791600998218, "count": 231790, "self": 0.0, "children": { "worker_root": { "total": 2494.7233527039466, "count": 231790, "is_parallel": true, "self": 1167.382374542029, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010776249999935317, "count": 1, "is_parallel": true, "self": 0.0003049300000839139, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007726949999096178, "count": 2, "is_parallel": true, "self": 0.0007726949999096178 } } }, "UnityEnvironment.step": { "total": 0.03400693499997942, "count": 1, "is_parallel": true, "self": 0.0003703559999621575, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002374829999780559, "count": 1, "is_parallel": true, "self": 0.0002374829999780559 }, "communicator.exchange": { "total": 0.032589311000037924, "count": 1, "is_parallel": true, "self": 0.032589311000037924 }, "steps_from_proto": { "total": 0.0008097850000012841, "count": 1, "is_parallel": true, "self": 0.00022993200002474623, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005798529999765378, "count": 2, "is_parallel": true, "self": 0.0005798529999765378 } } } } } } }, "UnityEnvironment.step": { "total": 1327.3409781619175, "count": 231789, "is_parallel": true, "self": 40.634418869893125, "children": { "UnityEnvironment._generate_step_input": { "total": 82.4230300610401, "count": 231789, "is_parallel": true, "self": 82.4230300610401 }, "communicator.exchange": { "total": 1103.6502710000545, "count": 231789, "is_parallel": true, "self": 1103.6502710000545 }, "steps_from_proto": { "total": 100.63325823092953, "count": 231789, "is_parallel": true, "self": 35.397105210954464, "children": { "_process_rank_one_or_two_observation": { "total": 65.23615301997506, "count": 463578, "is_parallel": true, "self": 65.23615301997506 } } } } } } } } } } }, "trainer_advance": { "total": 561.2878681218713, "count": 231790, "self": 6.753259892876713, "children": { "process_trajectory": { "total": 138.048690026994, "count": 231790, "self": 136.60352156299416, "children": { "RLTrainer._checkpoint": { "total": 1.4451684639998348, "count": 10, "self": 1.4451684639998348 } } }, "_update_policy": { "total": 416.48591820200056, "count": 97, "self": 355.7086488049962, "children": { "TorchPPOOptimizer.update": { "total": 60.777269397004375, "count": 2910, "self": 60.777269397004375 } } } } } } }, "trainer_threads": { "total": 1.0700000530050602e-06, "count": 1, "self": 1.0700000530050602e-06 }, "TrainerController._save_models": { "total": 0.12707272600027864, "count": 1, "self": 0.002142632999948546, "children": { "RLTrainer._checkpoint": { "total": 0.12493009300033009, "count": 1, "self": 0.12493009300033009 } } } } } } }