{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4094535112380981, "min": 1.4094535112380981, "max": 1.4306151866912842, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70715.1015625, "min": 68446.8203125, "max": 78910.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.36363636363636, "min": 77.36363636363636, "max": 434.0689655172414, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49358.0, "min": 49260.0, "max": 50352.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999341.0, "min": 49901.0, "max": 1999341.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999341.0, "min": 49901.0, "max": 1999341.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.455439329147339, "min": -0.01138994563370943, "max": 2.4928338527679443, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1566.5703125, "min": -1.3098437786102295, "max": 1566.5703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.740217578915593, "min": 1.8788280621818874, "max": 3.988598696210168, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2386.2588153481483, "min": 216.06522715091705, "max": 2386.2588153481483, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.740217578915593, "min": 1.8788280621818874, "max": 3.988598696210168, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2386.2588153481483, "min": 216.06522715091705, "max": 2386.2588153481483, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01755402562509213, "min": 0.013103631184397576, "max": 0.022513364823923136, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052662076875276395, "min": 0.026207262368795153, "max": 0.05974314630730078, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06363056484195921, "min": 0.02198577970266342, "max": 0.06363056484195921, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19089169452587765, "min": 0.04397155940532684, "max": 0.19089169452587765, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.360348879916665e-06, "min": 3.360348879916665e-06, "max": 0.00029529832656722497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0081046639749995e-05, "min": 1.0081046639749995e-05, "max": 0.0008438284687238499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112008333333335, "min": 0.10112008333333335, "max": 0.198432775, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30336025000000005, "min": 0.20738035, "max": 0.58127615, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.589215833333329e-05, "min": 6.589215833333329e-05, "max": 0.004921795472499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019767647499999987, "min": 0.00019767647499999987, "max": 0.014065679885000001, "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": "1678949896", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1678952221" }, "total": 2325.4861469830003, "count": 1, "self": 0.6054909010008487, "children": { "run_training.setup": { "total": 0.18979314999995722, "count": 1, "self": 0.18979314999995722 }, "TrainerController.start_learning": { "total": 2324.6908629319996, "count": 1, "self": 4.19040735605131, "children": { "TrainerController._reset_env": { "total": 9.08482404, "count": 1, "self": 9.08482404 }, "TrainerController.advance": { "total": 2311.292993129948, "count": 232719, "self": 4.625367590901078, "children": { "env_step": { "total": 1803.384434006015, "count": 232719, "self": 1521.0548698882055, "children": { "SubprocessEnvManager._take_step": { "total": 279.54769159099567, "count": 232719, "self": 16.685986655008776, "children": { "TorchPolicy.evaluate": { "total": 262.8617049359869, "count": 222932, "self": 262.8617049359869 } } }, "workers": { "total": 2.7818725268137428, "count": 232719, "self": 0.0, "children": { "worker_root": { "total": 2316.6771218189497, "count": 232719, "is_parallel": true, "self": 1080.375673858859, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010169230000087737, "count": 1, "is_parallel": true, "self": 0.00025368199999320495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007632410000155687, "count": 2, "is_parallel": true, "self": 0.0007632410000155687 } } }, "UnityEnvironment.step": { "total": 0.029014287999984845, "count": 1, "is_parallel": true, "self": 0.00034749400003875053, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003634189999957016, "count": 1, "is_parallel": true, "self": 0.0003634189999957016 }, "communicator.exchange": { "total": 0.027545332999977745, "count": 1, "is_parallel": true, "self": 0.027545332999977745 }, "steps_from_proto": { "total": 0.0007580419999726473, "count": 1, "is_parallel": true, "self": 0.00022463999999899897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005334019999736483, "count": 2, "is_parallel": true, "self": 0.0005334019999736483 } } } } } } }, "UnityEnvironment.step": { "total": 1236.3014479600906, "count": 232718, "is_parallel": true, "self": 38.32698993303575, "children": { "UnityEnvironment._generate_step_input": { "total": 77.37433628603634, "count": 232718, "is_parallel": true, "self": 77.37433628603634 }, "communicator.exchange": { "total": 1030.9207715529876, "count": 232718, "is_parallel": true, "self": 1030.9207715529876 }, "steps_from_proto": { "total": 89.67935018803081, "count": 232718, "is_parallel": true, "self": 34.18194665411289, "children": { "_process_rank_one_or_two_observation": { "total": 55.49740353391792, "count": 465436, "is_parallel": true, "self": 55.49740353391792 } } } } } } } } } } }, "trainer_advance": { "total": 503.28319153303215, "count": 232719, "self": 6.403013199021359, "children": { "process_trajectory": { "total": 141.33710418601106, "count": 232719, "self": 140.0931011840106, "children": { "RLTrainer._checkpoint": { "total": 1.2440030020004542, "count": 10, "self": 1.2440030020004542 } } }, "_update_policy": { "total": 355.54307414799973, "count": 97, "self": 297.69976765299873, "children": { "TorchPPOOptimizer.update": { "total": 57.843306495001, "count": 2910, "self": 57.843306495001 } } } } } } }, "trainer_threads": { "total": 1.0600001587590668e-06, "count": 1, "self": 1.0600001587590668e-06 }, "TrainerController._save_models": { "total": 0.12263734599991949, "count": 1, "self": 0.002044865999778267, "children": { "RLTrainer._checkpoint": { "total": 0.12059248000014122, "count": 1, "self": 0.12059248000014122 } } } } } } }