{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.41068696975708, "min": 1.410683274269104, "max": 1.426814079284668, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70063.1796875, "min": 69490.546875, "max": 75533.953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.89818181818181, "min": 87.75935828877006, "max": 396.57142857142856, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49444.0, "min": 48861.0, "max": 50286.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999996.0, "min": 49872.0, "max": 1999996.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999996.0, "min": 49872.0, "max": 1999996.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.40114426612854, "min": 0.04649478569626808, "max": 2.441274642944336, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1320.62939453125, "min": 5.811848163604736, "max": 1330.2021484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.692369801239534, "min": 1.8563373143672943, "max": 3.864070312222656, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2030.8033906817436, "min": 232.0421642959118, "max": 2105.3206179738045, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.692369801239534, "min": 1.8563373143672943, "max": 3.864070312222656, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2030.8033906817436, "min": 232.0421642959118, "max": 2105.3206179738045, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017562582618686266, "min": 0.013288589367645424, "max": 0.019262707060746228, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0526877478560588, "min": 0.02657717873529085, "max": 0.05778812118223868, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054441727283928126, "min": 0.023005366418510677, "max": 0.06353048825015625, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16332518185178438, "min": 0.046010732837021354, "max": 0.16332518185178438, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1716989427999966e-06, "min": 3.1716989427999966e-06, "max": 0.00029537985154005, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.51509682839999e-06, "min": 9.51509682839999e-06, "max": 0.0008442481685839499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1010572, "min": 0.1010572, "max": 0.19845995000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031716, "min": 0.20728295000000002, "max": 0.5814160500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.275427999999997e-05, "min": 6.275427999999997e-05, "max": 0.004923151505000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018826283999999992, "min": 0.00018826283999999992, "max": 0.014072660894999997, "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": "1683834506", "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": "1683836887" }, "total": 2380.695924743, "count": 1, "self": 0.778294896999796, "children": { "run_training.setup": { "total": 0.04054909899997483, "count": 1, "self": 0.04054909899997483 }, "TrainerController.start_learning": { "total": 2379.877080747, "count": 1, "self": 4.460346027938613, "children": { "TrainerController._reset_env": { "total": 4.857114429000035, "count": 1, "self": 4.857114429000035 }, "TrainerController.advance": { "total": 2370.3678918800615, "count": 231948, "self": 4.492743787975996, "children": { "env_step": { "total": 1845.6941609691214, "count": 231948, "self": 1560.274591068304, "children": { "SubprocessEnvManager._take_step": { "total": 282.5645661249091, "count": 231948, "self": 16.594861876000607, "children": { "TorchPolicy.evaluate": { "total": 265.9697042489085, "count": 222913, "self": 265.9697042489085 } } }, "workers": { "total": 2.8550037759082443, "count": 231948, "self": 0.0, "children": { "worker_root": { "total": 2371.734020758968, "count": 231948, "is_parallel": true, "self": 1099.0743429779386, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008688570000003892, "count": 1, "is_parallel": true, "self": 0.0002579629999672761, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006108940000331131, "count": 2, "is_parallel": true, "self": 0.0006108940000331131 } } }, "UnityEnvironment.step": { "total": 0.04578800799998817, "count": 1, "is_parallel": true, "self": 0.0003856589999600146, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002458600000068145, "count": 1, "is_parallel": true, "self": 0.0002458600000068145 }, "communicator.exchange": { "total": 0.04439455499999667, "count": 1, "is_parallel": true, "self": 0.04439455499999667 }, "steps_from_proto": { "total": 0.0007619340000246666, "count": 1, "is_parallel": true, "self": 0.0002617480000139949, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005001860000106717, "count": 2, "is_parallel": true, "self": 0.0005001860000106717 } } } } } } }, "UnityEnvironment.step": { "total": 1272.6596777810296, "count": 231947, "is_parallel": true, "self": 38.50040608495215, "children": { "UnityEnvironment._generate_step_input": { "total": 76.00332888806861, "count": 231947, "is_parallel": true, "self": 76.00332888806861 }, "communicator.exchange": { "total": 1065.180394100052, "count": 231947, "is_parallel": true, "self": 1065.180394100052 }, "steps_from_proto": { "total": 92.97554870795693, "count": 231947, "is_parallel": true, "self": 33.46772873986356, "children": { "_process_rank_one_or_two_observation": { "total": 59.50781996809337, "count": 463894, "is_parallel": true, "self": 59.50781996809337 } } } } } } } } } } }, "trainer_advance": { "total": 520.180987122964, "count": 231948, "self": 6.894586359972436, "children": { "process_trajectory": { "total": 131.5273529279927, "count": 231948, "self": 129.87291044599255, "children": { "RLTrainer._checkpoint": { "total": 1.6544424820001495, "count": 10, "self": 1.6544424820001495 } } }, "_update_policy": { "total": 381.75904783499885, "count": 97, "self": 321.3661484769868, "children": { "TorchPPOOptimizer.update": { "total": 60.39289935801207, "count": 2910, "self": 60.39289935801207 } } } } } } }, "trainer_threads": { "total": 1.2710002010862809e-06, "count": 1, "self": 1.2710002010862809e-06 }, "TrainerController._save_models": { "total": 0.191727138999795, "count": 1, "self": 0.0050375469995742606, "children": { "RLTrainer._checkpoint": { "total": 0.18668959200022073, "count": 1, "self": 0.18668959200022073 } } } } } } }