{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3693426251411438, "min": 0.36812862753868103, "max": 1.494761347770691, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11056.640625, "min": 10984.9580078125, "max": 45345.08203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5459956526756287, "min": -0.10052170604467392, "max": 0.5909854769706726, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.3268280029297, "min": -24.225730895996094, "max": 165.47593688964844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.7202028036117554, "min": -0.21068881452083588, "max": 1.7202028036117554, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 461.01434326171875, "min": -58.99286651611328, "max": 461.01434326171875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07005687046028786, "min": 0.06551805635034623, "max": 0.07255054541651507, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.98079618644403, "min": 0.4861065910994637, "max": 1.0682836636163606, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.3282941421901504, "min": 0.00028244519224593763, "max": 0.3282941421901504, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 4.596117990662106, "min": 0.003671787499197189, "max": 4.596117990662106, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.639768882014292e-06, "min": 7.639768882014292e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010695676434820007, "min": 0.00010695676434820007, "max": 0.0035085512304829994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254655714285717, "min": 0.10254655714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356518000000003, "min": 1.3691136000000002, "max": 2.5695170000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026440105857142884, "min": 0.00026440105857142884, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037016148200000034, "min": 0.0037016148200000034, "max": 0.1169747483, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01313258707523346, "min": 0.01313258707523346, "max": 0.3453860878944397, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18385621905326843, "min": 0.18385621905326843, "max": 2.4177026748657227, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 366.3333333333333, "min": 321.1208791208791, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28574.0, "min": 15984.0, "max": 32599.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5054256165256867, "min": -1.0000000521540642, "max": 1.6279031977217684, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.42319808900356, "min": -32.000001668930054, "max": 151.39499738812447, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5054256165256867, "min": -1.0000000521540642, "max": 1.6279031977217684, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.42319808900356, "min": -32.000001668930054, "max": 151.39499738812447, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05020725337985473, "min": 0.04541333345632365, "max": 6.338125875219703, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.916165763628669, "min": 3.916165763628669, "max": 101.41001400351524, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681761805", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1681763992" }, "total": 2186.711137513, "count": 1, "self": 0.5378457830001935, "children": { "run_training.setup": { "total": 0.19830761899993377, "count": 1, "self": 0.19830761899993377 }, "TrainerController.start_learning": { "total": 2185.9749841109997, "count": 1, "self": 1.3274526110349143, "children": { "TrainerController._reset_env": { "total": 4.127969364000023, "count": 1, "self": 4.127969364000023 }, "TrainerController.advance": { "total": 2180.4180531169645, "count": 63856, "self": 1.4171396329825257, "children": { "env_step": { "total": 1550.106284176955, "count": 63856, "self": 1444.7630942700234, "children": { "SubprocessEnvManager._take_step": { "total": 104.52762288296685, "count": 63856, "self": 4.772309941992489, "children": { "TorchPolicy.evaluate": { "total": 99.75531294097436, "count": 62552, "self": 99.75531294097436 } } }, "workers": { "total": 0.8155670239646042, "count": 63856, "self": 0.0, "children": { "worker_root": { "total": 2181.1032431690005, "count": 63856, "is_parallel": true, "self": 846.3810242849736, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00535000900003979, "count": 1, "is_parallel": true, "self": 0.004000617000201601, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013493919998381898, "count": 8, "is_parallel": true, "self": 0.0013493919998381898 } } }, "UnityEnvironment.step": { "total": 0.0527256950000492, "count": 1, "is_parallel": true, "self": 0.0005684270000756442, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000429528000040591, "count": 1, "is_parallel": true, "self": 0.000429528000040591 }, "communicator.exchange": { "total": 0.050127680999935365, "count": 1, "is_parallel": true, "self": 0.050127680999935365 }, "steps_from_proto": { "total": 0.0016000589999976, "count": 1, "is_parallel": true, "self": 0.00037218499983282527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012278740001647748, "count": 8, "is_parallel": true, "self": 0.0012278740001647748 } } } } } } }, "UnityEnvironment.step": { "total": 1334.722218884027, "count": 63855, "is_parallel": true, "self": 33.52364890806848, "children": { "UnityEnvironment._generate_step_input": { "total": 23.40606335596749, "count": 63855, "is_parallel": true, "self": 23.40606335596749 }, "communicator.exchange": { "total": 1181.9701114420072, "count": 63855, "is_parallel": true, "self": 1181.9701114420072 }, "steps_from_proto": { "total": 95.82239517798371, "count": 63855, "is_parallel": true, "self": 20.183972001866323, "children": { "_process_rank_one_or_two_observation": { "total": 75.63842317611739, "count": 510840, "is_parallel": true, "self": 75.63842317611739 } } } } } } } } } } }, "trainer_advance": { "total": 628.8946293070269, "count": 63856, "self": 2.5223227760202462, "children": { "process_trajectory": { "total": 110.00763283200979, "count": 63856, "self": 106.36404853800946, "children": { "RLTrainer._checkpoint": { "total": 3.643584294000334, "count": 33, "self": 3.643584294000334 } } }, "_update_policy": { "total": 516.3646736989969, "count": 445, "self": 330.62579184699143, "children": { "TorchPPOOptimizer.update": { "total": 185.73888185200542, "count": 22830, "self": 185.73888185200542 } } } } } } }, "trainer_threads": { "total": 1.1350002750987187e-06, "count": 1, "self": 1.1350002750987187e-06 }, "TrainerController._save_models": { "total": 0.10150788400005695, "count": 1, "self": 0.0014567620000889292, "children": { "RLTrainer._checkpoint": { "total": 0.10005112199996802, "count": 1, "self": 0.10005112199996802 } } } } } } }