{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13053016364574432, "min": 0.13053016364574432, "max": 0.34393319487571716, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 6543.2158203125, "min": 6508.48681640625, "max": 17504.82421875, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 226.53982300884957, "min": 217.42918454935622, "max": 335.7635135135135, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 51198.0, "min": 46619.0, "max": 51401.0, "count": 40 }, "Pyramids.Step.mean": { "value": 2999969.0, "min": 1049963.0, "max": 2999969.0, "count": 40 }, "Pyramids.Step.sum": { "value": 2999969.0, "min": 1049963.0, "max": 2999969.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8029366135597229, "min": 0.5550001859664917, "max": 0.8423917889595032, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 407.0888671875, "min": 256.965087890625, "max": 432.9893798828125, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016411546617746353, "min": -0.010096848011016846, "max": 0.0640997514128685, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.320653915405273, "min": -4.907068252563477, "max": 29.678184509277344, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7557530854457775, "min": 1.5966486237641122, "max": 1.7725354446606203, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 396.8001973107457, "min": 236.3039963170886, "max": 413.1451980918646, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7557530854457775, "min": 1.5966486237641122, "max": 1.7725354446606203, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 396.8001973107457, "min": 236.3039963170886, "max": 413.1451980918646, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016251778906775368, "min": 0.015597144257745558, "max": 0.034564408739219156, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6729020329312334, "min": 3.4313717367040226, "max": 5.288354537100531, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06941192193508731, "min": 0.06467020634631303, "max": 0.07191291106935192, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.6658861264420957, "min": 1.5020420119959725, "max": 1.725909865664446, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015384109843699404, "min": 0.012953029207141222, "max": 0.01637407874148907, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3692186362487857, "min": 0.2979196717642481, "max": 0.38210905112175486, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.429511690195832e-06, "min": 2.429511690195832e-06, "max": 0.00019744786896666374, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.830828056469996e-05, "min": 5.830828056469996e-05, "max": 0.004619409360197167, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10080980416666667, "min": 0.10080980416666667, "max": 0.16581594492753626, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.4194353, "min": 2.4194353, "max": 3.9398028333333333, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 9.089943624999996e-05, "min": 9.089943624999996e-05, "max": 0.0065850128982608705, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.002181586469999999, "min": 0.002181586469999999, "max": 0.15406630305000002, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006933924276381731, "min": 0.006791813764721155, "max": 0.010334798134863377, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16641418635845184, "min": 0.16214092075824738, "max": 0.23770035803318024, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686376080", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --resume", "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": "1686381186" }, "total": 5105.509026824, "count": 1, "self": 0.441498130000582, "children": { "run_training.setup": { "total": 0.03876343899992207, "count": 1, "self": 0.03876343899992207 }, "TrainerController.start_learning": { "total": 5105.028765255, "count": 1, "self": 2.787783518168908, "children": { "TrainerController._reset_env": { "total": 4.312965602999611, "count": 1, "self": 4.312965602999611 }, "TrainerController.advance": { "total": 5097.834866287832, "count": 131136, "self": 2.8199113848386332, "children": { "env_step": { "total": 3809.999547644815, "count": 131136, "self": 3591.752417211447, "children": { "SubprocessEnvManager._take_step": { "total": 216.53971534624998, "count": 131136, "self": 9.37691775055373, "children": { "TorchPolicy.evaluate": { "total": 207.16279759569625, "count": 125056, "self": 207.16279759569625 } } }, "workers": { "total": 1.7074150871176244, "count": 131136, "self": 0.0, "children": { "worker_root": { "total": 5093.981040424949, "count": 131136, "is_parallel": true, "self": 1737.400396409189, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001776224000423099, "count": 1, "is_parallel": true, "self": 0.0005706380006813561, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012055859997417429, "count": 8, "is_parallel": true, "self": 0.0012055859997417429 } } }, "UnityEnvironment.step": { "total": 0.08704309699987789, "count": 1, "is_parallel": true, "self": 0.0005678710003849119, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043306200041115517, "count": 1, "is_parallel": true, "self": 0.00043306200041115517 }, "communicator.exchange": { "total": 0.08425388799969369, "count": 1, "is_parallel": true, "self": 0.08425388799969369 }, "steps_from_proto": { "total": 0.0017882759993881336, "count": 1, "is_parallel": true, "self": 0.0003485019988147542, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014397740005733795, "count": 8, "is_parallel": true, "self": 0.0014397740005733795 } } } } } } }, "UnityEnvironment.step": { "total": 3356.5806440157603, "count": 131135, "is_parallel": true, "self": 66.04875748262566, "children": { "UnityEnvironment._generate_step_input": { "total": 44.59532830708031, "count": 131135, "is_parallel": true, "self": 44.59532830708031 }, "communicator.exchange": { "total": 3043.2339099858636, "count": 131135, "is_parallel": true, "self": 3043.2339099858636 }, "steps_from_proto": { "total": 202.70264824019068, "count": 131135, "is_parallel": true, "self": 40.38878473092791, "children": { "_process_rank_one_or_two_observation": { "total": 162.31386350926277, "count": 1049080, "is_parallel": true, "self": 162.31386350926277 } } } } } } } } } } }, "trainer_advance": { "total": 1285.0154072581781, "count": 131136, "self": 5.809300956127117, "children": { "process_trajectory": { "total": 224.75797619306013, "count": 131136, "self": 224.31268628105954, "children": { "RLTrainer._checkpoint": { "total": 0.44528991200058954, "count": 4, "self": 0.44528991200058954 } } }, "_update_policy": { "total": 1054.4481301089909, "count": 947, "self": 678.76073158895, "children": { "TorchPPOOptimizer.update": { "total": 375.6873985200409, "count": 45561, "self": 375.6873985200409 } } } } } } }, "trainer_threads": { "total": 9.899995347950608e-07, "count": 1, "self": 9.899995347950608e-07 }, "TrainerController._save_models": { "total": 0.09314885599997069, "count": 1, "self": 0.0017387700008839602, "children": { "RLTrainer._checkpoint": { "total": 0.09141008599908673, "count": 1, "self": 0.09141008599908673 } } } } } } }