{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4019339084625244, "min": 1.4019339084625244, "max": 1.4266701936721802, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70424.75, "min": 68250.4765625, "max": 78008.25, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.48722316865417, "min": 81.03770491803279, "max": 371.52985074626866, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49594.0, "min": 48755.0, "max": 50428.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999459.0, "min": 49873.0, "max": 1999459.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999459.0, "min": 49873.0, "max": 1999459.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4398016929626465, "min": 0.08045613765716553, "max": 2.4885618686676025, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1432.16357421875, "min": 10.861578941345215, "max": 1512.298583984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7361067780237995, "min": 1.7236467802966082, "max": 3.9883776538498035, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2193.0946786999702, "min": 232.69231534004211, "max": 2319.0197598338127, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7361067780237995, "min": 1.7236467802966082, "max": 3.9883776538498035, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2193.0946786999702, "min": 232.69231534004211, "max": 2319.0197598338127, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01639008173264705, "min": 0.014390592945710523, "max": 0.020712317807677513, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04917024519794116, "min": 0.028781185891421045, "max": 0.06070394592437271, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05617284145620135, "min": 0.021242887681970996, "max": 0.06481898712615172, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16851852436860404, "min": 0.04248577536394199, "max": 0.18089665696024892, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7617987460999893e-06, "min": 3.7617987460999893e-06, "max": 0.000295332976555675, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1285396238299968e-05, "min": 1.1285396238299968e-05, "max": 0.000844272018576, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125390000000002, "min": 0.10125390000000002, "max": 0.19844432500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037617000000001, "min": 0.2076519, "max": 0.5814240000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.256960999999983e-05, "min": 7.256960999999983e-05, "max": 0.004922371817499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002177088299999995, "min": 0.0002177088299999995, "max": 0.014073057600000004, "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": "1683790829", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683793230" }, "total": 2401.451250457, "count": 1, "self": 0.43703592999963803, "children": { "run_training.setup": { "total": 0.03893662799998765, "count": 1, "self": 0.03893662799998765 }, "TrainerController.start_learning": { "total": 2400.975277899, "count": 1, "self": 4.349105583962682, "children": { "TrainerController._reset_env": { "total": 4.257930885000064, "count": 1, "self": 4.257930885000064 }, "TrainerController.advance": { "total": 2392.2423243220373, "count": 232844, "self": 4.365160577079678, "children": { "env_step": { "total": 1863.758963056934, "count": 232844, "self": 1573.7498562758221, "children": { "SubprocessEnvManager._take_step": { "total": 287.22487466108123, "count": 232844, "self": 16.67135734005035, "children": { "TorchPolicy.evaluate": { "total": 270.5535173210309, "count": 222980, "self": 270.5535173210309 } } }, "workers": { "total": 2.7842321200305378, "count": 232844, "self": 0.0, "children": { "worker_root": { "total": 2393.0264060109876, "count": 232844, "is_parallel": true, "self": 1104.4634294750263, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009473009999965143, "count": 1, "is_parallel": true, "self": 0.0002593550000256073, "children": { "_process_rank_one_or_two_observation": { "total": 0.000687945999970907, "count": 2, "is_parallel": true, "self": 0.000687945999970907 } } }, "UnityEnvironment.step": { "total": 0.0672853319999831, "count": 1, "is_parallel": true, "self": 0.0003359080000109316, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026281899999958114, "count": 1, "is_parallel": true, "self": 0.00026281899999958114 }, "communicator.exchange": { "total": 0.06595819099993605, "count": 1, "is_parallel": true, "self": 0.06595819099993605 }, "steps_from_proto": { "total": 0.0007284140000365369, "count": 1, "is_parallel": true, "self": 0.00018357800001922442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005448360000173125, "count": 2, "is_parallel": true, "self": 0.0005448360000173125 } } } } } } }, "UnityEnvironment.step": { "total": 1288.5629765359613, "count": 232843, "is_parallel": true, "self": 38.38951571896223, "children": { "UnityEnvironment._generate_step_input": { "total": 78.1576609419161, "count": 232843, "is_parallel": true, "self": 78.1576609419161 }, "communicator.exchange": { "total": 1078.4928312470406, "count": 232843, "is_parallel": true, "self": 1078.4928312470406 }, "steps_from_proto": { "total": 93.52296862804235, "count": 232843, "is_parallel": true, "self": 34.02998257501895, "children": { "_process_rank_one_or_two_observation": { "total": 59.4929860530234, "count": 465686, "is_parallel": true, "self": 59.4929860530234 } } } } } } } } } } }, "trainer_advance": { "total": 524.1182006880238, "count": 232844, "self": 6.730542806930998, "children": { "process_trajectory": { "total": 136.0333614760924, "count": 232844, "self": 134.6582759370923, "children": { "RLTrainer._checkpoint": { "total": 1.3750855390001107, "count": 10, "self": 1.3750855390001107 } } }, "_update_policy": { "total": 381.35429640500035, "count": 97, "self": 321.0166998420127, "children": { "TorchPPOOptimizer.update": { "total": 60.33759656298764, "count": 2910, "self": 60.33759656298764 } } } } } } }, "trainer_threads": { "total": 1.0310000106983352e-06, "count": 1, "self": 1.0310000106983352e-06 }, "TrainerController._save_models": { "total": 0.12591607700005625, "count": 1, "self": 0.0024560520000704855, "children": { "RLTrainer._checkpoint": { "total": 0.12346002499998576, "count": 1, "self": 0.12346002499998576 } } } } } } }