{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.3712373673915863, "min": 0.332507848739624, "max": 1.1783778667449951, "count": 10 }, "PushBlock.Policy.Entropy.sum": { "value": 37016.8203125, "min": 33261.42578125, "max": 118931.3203125, "count": 10 }, "PushBlock.Step.mean": { "value": 999996.0, "min": 99985.0, "max": 999996.0, "count": 10 }, "PushBlock.Step.sum": { "value": 999996.0, "min": 99985.0, "max": 999996.0, "count": 10 }, "PushBlock.Policy.ExtrinsicValue.mean": { "value": 2.9794063568115234, "min": 1.3723224401474, "max": 2.9794063568115234, "count": 10 }, "PushBlock.Policy.ExtrinsicValue.sum": { "value": 7076.08984375, "min": 2294.523193359375, "max": 7076.08984375, "count": 10 }, "PushBlock.Losses.PolicyLoss.mean": { "value": -2.602618768266778, "min": -2.602618768266778, "max": -1.1773443270676254, "count": 10 }, "PushBlock.Losses.PolicyLoss.sum": { "value": -26031.39292020431, "min": -26031.39292020431, "max": -11771.088582022117, "count": 10 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.003780544149984188, "min": 0.0012007021113701695, "max": 0.004268766598163566, "count": 10 }, "PushBlock.Losses.ValueLoss.sum": { "value": 37.81300258814185, "min": 12.004619709478956, "max": 42.67912844843933, "count": 10 }, "PushBlock.Losses.Q1Loss.mean": { "value": 0.018336053637291166, "min": 0.005078324491846632, "max": 0.022642880998674154, "count": 10 }, "PushBlock.Losses.Q1Loss.sum": { "value": 183.39720848018624, "min": 50.77308826948263, "max": 226.3835242247442, "count": 10 }, "PushBlock.Losses.Q2Loss.mean": { "value": 0.01862863995858222, "min": 0.005102800202005284, "max": 0.022636636116811028, "count": 10 }, "PushBlock.Losses.Q2Loss.sum": { "value": 186.32365686573937, "min": 51.01779641964883, "max": 226.32108789587664, "count": 10 }, "PushBlock.Policy.DiscreteEntropyCoeff.mean": { "value": 0.0163893654807615, "min": 0.0043324678179269445, "max": 0.016766645388260507, "count": 10 }, "PushBlock.Policy.DiscreteEntropyCoeff.sum": { "value": 163.9264335385765, "min": 43.320345711451516, "max": 167.63292059182857, "count": 10 }, "PushBlock.Policy.ContinuousEntropyCoeff.mean": { "value": 0.04999999701976776, "min": 0.04999999701976776, "max": 0.04999999701976776, "count": 10 }, "PushBlock.Policy.ContinuousEntropyCoeff.sum": { "value": 500.09997019171715, "min": 499.8999702036381, "max": 500.09997019171715, "count": 10 }, "PushBlock.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.00030000000000000003, "count": 10 }, "PushBlock.Policy.LearningRate.sum": { "value": 3.0005999999999995, "min": 2.9993999999999996, "max": 3.0005999999999995, "count": 10 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 66.61394101876675, "min": 66.61394101876675, "max": 420.02272727272725, "count": 10 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 99388.0, "min": 92405.0, "max": 103213.0, "count": 10 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.801977244611157, "min": 3.5790771414003215, "max": 4.801977244611157, "count": 10 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 7159.748071715236, "min": 787.4502075128257, "max": 7159.748071715236, "count": 10 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.801977244611157, "min": 3.5790771414003215, "max": 4.801977244611157, "count": 10 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 7159.748071715236, "min": 787.4502075128257, "max": 7159.748071715236, "count": 10 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1661242875", "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/sac/PushBlock.yaml --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": "1661246787" }, "total": 3912.0366775039997, "count": 1, "self": 0.5475908200000958, "children": { "run_training.setup": { "total": 0.05234334000004992, "count": 1, "self": 0.05234334000004992 }, "TrainerController.start_learning": { "total": 3911.4367433439998, "count": 1, "self": 1.580641356011256, "children": { "TrainerController._reset_env": { "total": 7.074140403000001, "count": 1, "self": 7.074140403000001 }, "TrainerController.advance": { "total": 3902.694383691988, "count": 37262, "self": 1.580514214001596, "children": { "env_step": { "total": 793.1453913120151, "count": 37262, "self": 737.9936400500044, "children": { "SubprocessEnvManager._take_step": { "total": 54.35588945700397, "count": 37262, "self": 3.792237451970834, "children": { "TorchPolicy.evaluate": { "total": 50.563652005033134, "count": 31271, "self": 12.526417376005554, "children": { "TorchPolicy.sample_actions": { "total": 38.03723462902758, "count": 31271, "self": 38.03723462902758 } } } } }, "workers": { "total": 0.795861805006723, "count": 37262, "self": 0.0, "children": { "worker_root": { "total": 3908.2525772149925, "count": 37262, "is_parallel": true, "self": 3276.9526831860576, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010188010000035774, "count": 1, "is_parallel": true, "self": 0.003747636000014154, "children": { "_process_rank_one_or_two_observation": { "total": 0.00644037400002162, "count": 4, "is_parallel": true, "self": 0.00644037400002162 } } }, "UnityEnvironment.step": { "total": 0.04184069600000839, "count": 1, "is_parallel": true, "self": 0.0006491750000350294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004904909999936535, "count": 1, "is_parallel": true, "self": 0.0004904909999936535 }, "communicator.exchange": { "total": 0.03787494699997751, "count": 1, "is_parallel": true, "self": 0.03787494699997751 }, "steps_from_proto": { "total": 0.0028260830000021997, "count": 1, "is_parallel": true, "self": 0.0006083400000989059, "children": { "_process_rank_one_or_two_observation": { "total": 0.002217742999903294, "count": 4, "is_parallel": true, "self": 0.002217742999903294 } } } } } } }, "UnityEnvironment.step": { "total": 631.299894028935, "count": 37261, "is_parallel": true, "self": 29.42326764798338, "children": { "UnityEnvironment._generate_step_input": { "total": 24.117601095029386, "count": 37261, "is_parallel": true, "self": 24.117601095029386 }, "communicator.exchange": { "total": 483.2400676249816, "count": 37261, "is_parallel": true, "self": 483.2400676249816 }, "steps_from_proto": { "total": 94.5189576609406, "count": 37261, "is_parallel": true, "self": 18.776853208786463, "children": { "_process_rank_one_or_two_observation": { "total": 75.74210445215414, "count": 149044, "is_parallel": true, "self": 75.74210445215414 } } } } } } } } } } }, "trainer_advance": { "total": 3107.9684781659716, "count": 37262, "self": 4.5975981459441755, "children": { "process_trajectory": { "total": 134.20930266298467, "count": 37262, "self": 133.87402496598463, "children": { "RLTrainer._checkpoint": { "total": 0.33527769700003773, "count": 2, "self": 0.33527769700003773 } } }, "_update_policy": { "total": 2969.161577357043, "count": 37198, "self": 1.1008915340235035, "children": { "SACTrainer._update_policy": { "total": 2968.0606858230194, "count": 37198, "self": 705.290458069047, "children": { "TorchSACOptimizer.update": { "total": 2262.7702277539724, "count": 99999, "self": 2262.7702277539724 } } } } } } } } }, "trainer_threads": { "total": 1.2820000847568735e-06, "count": 1, "self": 1.2820000847568735e-06 }, "TrainerController._save_models": { "total": 0.08757661100025871, "count": 1, "self": 0.0010379790001024958, "children": { "RLTrainer._checkpoint": { "total": 0.08653863200015621, "count": 1, "self": 0.08653863200015621 } } } } } } }