{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2998795807361603, "min": 0.2998795807361603, "max": 1.4496777057647705, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8967.5986328125, "min": 8967.5986328125, "max": 43977.421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6211113929748535, "min": -0.10344476997852325, "max": 0.6849846839904785, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.3956298828125, "min": -24.826744079589844, "max": 195.22064208984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01656731404364109, "min": 0.0066413888707757, "max": 0.2593795359134674, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.705117225646973, "min": 1.8463060855865479, "max": 61.47294998168945, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0680502437268539, "min": 0.06624737396650081, "max": 0.07324356189605101, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9527034121759548, "min": 0.493056342613063, "max": 1.045916427722356, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016668645421131733, "min": 0.0006032778104597699, "max": 0.01732480638574565, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23336103589584428, "min": 0.007239333725517239, "max": 0.24254728940043907, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.345468980114285e-06, "min": 7.345468980114285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001028365657216, "min": 0.0001028365657216, "max": 0.0035077301307567003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244845714285715, "min": 0.10244845714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342784000000002, "min": 1.3886848, "max": 2.5692432999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002546008685714286, "min": 0.0002546008685714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00356441216, "min": 0.00356441216, "max": 0.11694740567, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011610016226768494, "min": 0.011610016226768494, "max": 0.34201645851135254, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1625402271747589, "min": 0.1625402271747589, "max": 2.3941152095794678, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 300.3207547169811, "min": 295.4183673469388, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31834.0, "min": 15984.0, "max": 32710.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6808056418063506, "min": -1.0000000521540642, "max": 1.7045816140515464, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.16539803147316, "min": -30.725001737475395, "max": 178.16539803147316, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6808056418063506, "min": -1.0000000521540642, "max": 1.7045816140515464, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.16539803147316, "min": -30.725001737475395, "max": 178.16539803147316, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03615061890899219, "min": 0.03615061890899219, "max": 7.062693669460714, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8319656043531722, "min": 3.583511717741203, "max": 113.00309871137142, "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": "1686002584", "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/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": "1686004782" }, "total": 2197.493461491, "count": 1, "self": 0.47530546899997717, "children": { "run_training.setup": { "total": 0.05878056699998524, "count": 1, "self": 0.05878056699998524 }, "TrainerController.start_learning": { "total": 2196.959375455, "count": 1, "self": 1.2388562359615207, "children": { "TrainerController._reset_env": { "total": 4.325028324999948, "count": 1, "self": 4.325028324999948 }, "TrainerController.advance": { "total": 2191.3029616150384, "count": 64000, "self": 1.2815704500203537, "children": { "env_step": { "total": 1555.7241794750098, "count": 64000, "self": 1449.964436231954, "children": { "SubprocessEnvManager._take_step": { "total": 105.0128216770429, "count": 64000, "self": 4.608041462992787, "children": { "TorchPolicy.evaluate": { "total": 100.4047802140501, "count": 62562, "self": 100.4047802140501 } } }, "workers": { "total": 0.7469215660128157, "count": 64000, "self": 0.0, "children": { "worker_root": { "total": 2192.311874466068, "count": 64000, "is_parallel": true, "self": 850.1238659970991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027934869999626244, "count": 1, "is_parallel": true, "self": 0.0009180469999137131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018754400000489113, "count": 8, "is_parallel": true, "self": 0.0018754400000489113 } } }, "UnityEnvironment.step": { "total": 0.04482490999998845, "count": 1, "is_parallel": true, "self": 0.0006098199999087228, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004734430001462897, "count": 1, "is_parallel": true, "self": 0.0004734430001462897 }, "communicator.exchange": { "total": 0.04205245000002833, "count": 1, "is_parallel": true, "self": 0.04205245000002833 }, "steps_from_proto": { "total": 0.001689196999905107, "count": 1, "is_parallel": true, "self": 0.00032643899999129644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013627579999138106, "count": 8, "is_parallel": true, "self": 0.0013627579999138106 } } } } } } }, "UnityEnvironment.step": { "total": 1342.1880084689687, "count": 63999, "is_parallel": true, "self": 31.031308241090528, "children": { "UnityEnvironment._generate_step_input": { "total": 22.3780337449557, "count": 63999, "is_parallel": true, "self": 22.3780337449557 }, "communicator.exchange": { "total": 1192.7251061700053, "count": 63999, "is_parallel": true, "self": 1192.7251061700053 }, "steps_from_proto": { "total": 96.05356031291717, "count": 63999, "is_parallel": true, "self": 19.300981968859332, "children": { "_process_rank_one_or_two_observation": { "total": 76.75257834405784, "count": 511992, "is_parallel": true, "self": 76.75257834405784 } } } } } } } } } } }, "trainer_advance": { "total": 634.2972116900085, "count": 64000, "self": 2.46552353801917, "children": { "process_trajectory": { "total": 106.53733751398977, "count": 64000, "self": 106.27801345098987, "children": { "RLTrainer._checkpoint": { "total": 0.2593240629998945, "count": 2, "self": 0.2593240629998945 } } }, "_update_policy": { "total": 525.2943506379995, "count": 450, "self": 337.8089235699963, "children": { "TorchPPOOptimizer.update": { "total": 187.48542706800322, "count": 22812, "self": 187.48542706800322 } } } } } } }, "trainer_threads": { "total": 7.650000952708069e-07, "count": 1, "self": 7.650000952708069e-07 }, "TrainerController._save_models": { "total": 0.09252851400015061, "count": 1, "self": 0.0013740320000579231, "children": { "RLTrainer._checkpoint": { "total": 0.09115448200009268, "count": 1, "self": 0.09115448200009268 } } } } } } }