{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.33722591400146484, "min": 0.33722591400146484, "max": 1.8695212602615356, "count": 33 }, "PushBlock.Policy.Entropy.sum": { "value": 20265.927734375, "min": 20265.927734375, "max": 113427.59375, "count": 33 }, "PushBlock.Step.mean": { "value": 1979990.0, "min": 59960.0, "max": 1979990.0, "count": 33 }, "PushBlock.Step.sum": { "value": 1979990.0, "min": 59960.0, "max": 1979990.0, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.mean": { "value": 3.8565382957458496, "min": 0.07406709343194962, "max": 4.076359748840332, "count": 33 }, "PushBlock.Policy.ExtrinsicValueEstimate.sum": { "value": 8538.3759765625, "min": 71.10440826416016, "max": 9905.5546875, "count": 33 }, "PushBlock.Losses.PolicyLoss.mean": { "value": 0.07065016600429135, "min": 0.06565261727142757, "max": 0.07092491090103673, "count": 33 }, "PushBlock.Losses.PolicyLoss.sum": { "value": 2.048854814124449, "min": 1.559444420121733, "max": 2.056822416130065, "count": 33 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.21901374554593417, "min": 0.059389760893424265, "max": 0.36179679329743186, "count": 33 }, "PushBlock.Losses.ValueLoss.sum": { "value": 6.351398620832091, "min": 1.3065747396553338, "max": 10.492107005625524, "count": 33 }, "PushBlock.Policy.LearningRate.mean": { "value": 7.56613885729655e-06, "min": 7.56613885729655e-06, "max": 0.0002950413425619773, "count": 33 }, "PushBlock.Policy.LearningRate.sum": { "value": 0.00021941802686159995, "min": 0.00021941802686159995, "max": 0.0083061859312714, "count": 33 }, "PushBlock.Policy.Epsilon.mean": { "value": 0.10252201379310344, "min": 0.10252201379310344, "max": 0.19834711363636365, "count": 33 }, "PushBlock.Policy.Epsilon.sum": { "value": 2.9731384, "min": 2.9731384, "max": 5.668728600000002, "count": 33 }, "PushBlock.Policy.Beta.mean": { "value": 0.0002619491779310344, "min": 0.0002619491779310344, "max": 0.009834876652272728, "count": 33 }, "PushBlock.Policy.Beta.sum": { "value": 0.007596526159999999, "min": 0.007596526159999999, "max": 0.27688598713999996, "count": 33 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 30.343201754385966, "min": 26.751054852320674, "max": 744.2549019607843, "count": 33 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 55346.0, "min": 37957.0, "max": 71322.0, "count": 33 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.92248410635615, "min": 1.2156862590973283, "max": 4.944507263670719, "count": 33 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 8983.533494099975, "min": 61.99999921396375, "max": 10541.689486145973, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.92248410635615, "min": 1.2156862590973283, "max": 4.944507263670719, "count": 33 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 8983.533494099975, "min": 61.99999921396375, "max": 10541.689486145973, "count": 33 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1656924848", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --resume --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --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": "1656926937" }, "total": 2088.862127583, "count": 1, "self": 0.38092879000032553, "children": { "run_training.setup": { "total": 0.04165218200000709, "count": 1, "self": 0.04165218200000709 }, "TrainerController.start_learning": { "total": 2088.439546611, "count": 1, "self": 2.24190991901105, "children": { "TrainerController._reset_env": { "total": 6.316924286000017, "count": 1, "self": 6.316924286000017 }, "TrainerController.advance": { "total": 2079.820143014989, "count": 96875, "self": 2.254332793024332, "children": { "env_step": { "total": 1235.921350959969, "count": 96875, "self": 1132.0936363799929, "children": { "SubprocessEnvManager._take_step": { "total": 102.73826761500209, "count": 96875, "self": 5.526802036970594, "children": { "TorchPolicy.evaluate": { "total": 97.2114655780315, "count": 62519, "self": 31.295723613979362, "children": { "TorchPolicy.sample_actions": { "total": 65.91574196405213, "count": 62519, "self": 65.91574196405213 } } } } }, "workers": { "total": 1.0894469649739449, "count": 96875, "self": 0.0, "children": { "worker_root": { "total": 2083.917374952014, "count": 96875, "is_parallel": true, "self": 1107.3758011870466, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002442584000050374, "count": 1, "is_parallel": true, "self": 0.000716575000069497, "children": { "_process_rank_one_or_two_observation": { "total": 0.001726008999980877, "count": 4, "is_parallel": true, "self": 0.001726008999980877 } } }, "UnityEnvironment.step": { "total": 0.03243801899998289, "count": 1, "is_parallel": true, "self": 0.0007644500000196786, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007314270000051692, "count": 1, "is_parallel": true, "self": 0.0007314270000051692 }, "communicator.exchange": { "total": 0.028701266999973996, "count": 1, "is_parallel": true, "self": 0.028701266999973996 }, "steps_from_proto": { "total": 0.002240874999984044, "count": 1, "is_parallel": true, "self": 0.0004186319999917032, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018222429999923406, "count": 4, "is_parallel": true, "self": 0.0018222429999923406 } } } } } } }, "UnityEnvironment.step": { "total": 976.5415737649676, "count": 96874, "is_parallel": true, "self": 47.16540336711739, "children": { "UnityEnvironment._generate_step_input": { "total": 42.528755005947914, "count": 96874, "is_parallel": true, "self": 42.528755005947914 }, "communicator.exchange": { "total": 744.8899298919922, "count": 96874, "is_parallel": true, "self": 744.8899298919922 }, "steps_from_proto": { "total": 141.95748549991004, "count": 96874, "is_parallel": true, "self": 30.022575108893875, "children": { "_process_rank_one_or_two_observation": { "total": 111.93491039101616, "count": 387496, "is_parallel": true, "self": 111.93491039101616 } } } } } } } } } } }, "trainer_advance": { "total": 841.6444592619955, "count": 96875, "self": 3.980088374927732, "children": { "process_trajectory": { "total": 249.56262402706557, "count": 96875, "self": 249.29092566906593, "children": { "RLTrainer._checkpoint": { "total": 0.2716983579996395, "count": 4, "self": 0.2716983579996395 } } }, "_update_policy": { "total": 588.1017468600022, "count": 957, "self": 309.67303375698, "children": { "TorchPPOOptimizer.update": { "total": 278.42871310302223, "count": 46263, "self": 278.42871310302223 } } } } } } }, "trainer_threads": { "total": 1.021000116452342e-06, "count": 1, "self": 1.021000116452342e-06 }, "TrainerController._save_models": { "total": 0.06056837000005544, "count": 1, "self": 0.0008598590002293349, "children": { "RLTrainer._checkpoint": { "total": 0.0597085109998261, "count": 1, "self": 0.0597085109998261 } } } } } } }