{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4017964601516724, "min": 1.4017964601516724, "max": 1.4267747402191162, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70051.9765625, "min": 68313.8046875, "max": 77681.59375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 113.95227272727273, "min": 87.0, "max": 408.3333333333333, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50139.0, "min": 48894.0, "max": 50225.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999911.0, "min": 49999.0, "max": 1999911.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999911.0, "min": 49999.0, "max": 1999911.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3085570335388184, "min": 0.12224842607975006, "max": 2.3807268142700195, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1015.76513671875, "min": 14.914307594299316, "max": 1307.89306640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7009384858337318, "min": 1.9096603481495966, "max": 3.9470964206589594, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1628.412933766842, "min": 232.9785624742508, "max": 2120.830377280712, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7009384858337318, "min": 1.9096603481495966, "max": 3.9470964206589594, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1628.412933766842, "min": 232.9785624742508, "max": 2120.830377280712, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016835854569944783, "min": 0.014764060612408987, "max": 0.020352439266813842, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05050756370983435, "min": 0.029528121224817974, "max": 0.05648852807256238, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04747331481840875, "min": 0.021108336467295884, "max": 0.05933707791070143, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14241994445522627, "min": 0.04221667293459177, "max": 0.16270600308974584, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1946989351333244e-06, "min": 3.1946989351333244e-06, "max": 0.0002953005015664999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.584096805399973e-06, "min": 9.584096805399973e-06, "max": 0.0008441466186178, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1010648666666667, "min": 0.1010648666666667, "max": 0.19843349999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031946000000001, "min": 0.20729495, "max": 0.5813822, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.313684666666655e-05, "min": 6.313684666666655e-05, "max": 0.00492183165, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018941053999999965, "min": 0.00018941053999999965, "max": 0.014070971779999998, "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": "1673888188", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673890428" }, "total": 2239.869813008, "count": 1, "self": 0.3925941350003086, "children": { "run_training.setup": { "total": 0.11068479699997624, "count": 1, "self": 0.11068479699997624 }, "TrainerController.start_learning": { "total": 2239.366534076, "count": 1, "self": 3.835275831839681, "children": { "TrainerController._reset_env": { "total": 10.758189276999929, "count": 1, "self": 10.758189276999929 }, "TrainerController.advance": { "total": 2224.6495969071602, "count": 231458, "self": 4.209717739116968, "children": { "env_step": { "total": 1757.861914255886, "count": 231458, "self": 1471.3459861399501, "children": { "SubprocessEnvManager._take_step": { "total": 283.85204681495657, "count": 231458, "self": 14.524194648990033, "children": { "TorchPolicy.evaluate": { "total": 269.32785216596653, "count": 222950, "self": 66.57481907196211, "children": { "TorchPolicy.sample_actions": { "total": 202.75303309400442, "count": 222950, "self": 202.75303309400442 } } } } }, "workers": { "total": 2.6638813009792557, "count": 231458, "self": 0.0, "children": { "worker_root": { "total": 2231.163401660001, "count": 231458, "is_parallel": true, "self": 1026.082925527, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019854479999139585, "count": 1, "is_parallel": true, "self": 0.0003196469999693363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016658009999446222, "count": 2, "is_parallel": true, "self": 0.0016658009999446222 } } }, "UnityEnvironment.step": { "total": 0.028550509000069724, "count": 1, "is_parallel": true, "self": 0.00027837899983751413, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000196004000144967, "count": 1, "is_parallel": true, "self": 0.000196004000144967 }, "communicator.exchange": { "total": 0.02717914799995924, "count": 1, "is_parallel": true, "self": 0.02717914799995924 }, "steps_from_proto": { "total": 0.0008969780001280014, "count": 1, "is_parallel": true, "self": 0.0002619069998672785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006350710002607229, "count": 2, "is_parallel": true, "self": 0.0006350710002607229 } } } } } } }, "UnityEnvironment.step": { "total": 1205.080476133001, "count": 231457, "is_parallel": true, "self": 34.390609418283475, "children": { "UnityEnvironment._generate_step_input": { "total": 78.5467456469205, "count": 231457, "is_parallel": true, "self": 78.5467456469205 }, "communicator.exchange": { "total": 997.2111063528553, "count": 231457, "is_parallel": true, "self": 997.2111063528553 }, "steps_from_proto": { "total": 94.93201471494172, "count": 231457, "is_parallel": true, "self": 41.04119204705967, "children": { "_process_rank_one_or_two_observation": { "total": 53.89082266788205, "count": 462914, "is_parallel": true, "self": 53.89082266788205 } } } } } } } } } } }, "trainer_advance": { "total": 462.5779649121573, "count": 231458, "self": 6.079695142190758, "children": { "process_trajectory": { "total": 145.5650935009669, "count": 231458, "self": 144.37462989996698, "children": { "RLTrainer._checkpoint": { "total": 1.1904636009999194, "count": 10, "self": 1.1904636009999194 } } }, "_update_policy": { "total": 310.93317626899966, "count": 97, "self": 257.4630236380101, "children": { "TorchPPOOptimizer.update": { "total": 53.47015263098956, "count": 2910, "self": 53.47015263098956 } } } } } } }, "trainer_threads": { "total": 7.720000212430023e-07, "count": 1, "self": 7.720000212430023e-07 }, "TrainerController._save_models": { "total": 0.12347128800001883, "count": 1, "self": 0.002091889999974228, "children": { "RLTrainer._checkpoint": { "total": 0.1213793980000446, "count": 1, "self": 0.1213793980000446 } } } } } } }