{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3840648829936981, "min": 0.3840648829936981, "max": 1.409225583076477, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11503.51171875, "min": 11503.51171875, "max": 42750.265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989950.0, "min": 29952.0, "max": 989950.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989950.0, "min": 29952.0, "max": 989950.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2566322386264801, "min": -0.09082499891519547, "max": 0.33194172382354736, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 65.95448303222656, "min": -21.888824462890625, "max": 86.96873474121094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006094653625041246, "min": -0.02837957814335823, "max": 0.38932013511657715, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5663260221481323, "min": -7.06651496887207, "max": 93.8261489868164, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06581748453177921, "min": 0.06581748453177921, "max": 0.07374441271254217, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.921444783444909, "min": 0.4846885674275142, "max": 1.0922513815942996, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012466696772877818, "min": 0.0004186935525353345, "max": 0.014715569629350042, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17453375482028946, "min": 0.005443016182959348, "max": 0.19289142936930362, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2837332864071426e-06, "min": 7.2837332864071426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010197226600969999, "min": 0.00010197226600969999, "max": 0.0035081708306097994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242787857142856, "min": 0.10242787857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339902999999998, "min": 1.3886848, "max": 2.5693902, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002525450692857143, "min": 0.0002525450692857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00353563097, "min": 0.00353563097, "max": 0.11696208098, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009717540815472603, "min": 0.009717540815472603, "max": 0.6403778195381165, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13604557514190674, "min": 0.13604557514190674, "max": 4.482644557952881, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 584.7592592592592, "min": 455.61764705882354, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31577.0, "min": 15984.0, "max": 32683.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0818110813421231, "min": -1.0000000521540642, "max": 1.309002916164258, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.41779839247465, "min": -29.70780162513256, "max": 89.01219829916954, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0818110813421231, "min": -1.0000000521540642, "max": 1.309002916164258, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.41779839247465, "min": -29.70780162513256, "max": 89.01219829916954, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05885699309874326, "min": 0.04836528204289019, "max": 14.279201205819845, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.178277627332136, "min": 2.748710427462356, "max": 228.46721929311752, "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": "1681498297", "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": "1681500453" }, "total": 2156.337426397, "count": 1, "self": 0.5382677630004764, "children": { "run_training.setup": { "total": 0.10766148899983818, "count": 1, "self": 0.10766148899983818 }, "TrainerController.start_learning": { "total": 2155.6914971449996, "count": 1, "self": 1.4521884700247938, "children": { "TrainerController._reset_env": { "total": 3.839629939999895, "count": 1, "self": 3.839629939999895 }, "TrainerController.advance": { "total": 2150.295063453975, "count": 63427, "self": 1.4520742489858094, "children": { "env_step": { "total": 1501.2235828050464, "count": 63427, "self": 1392.8588598431043, "children": { "SubprocessEnvManager._take_step": { "total": 107.492017702976, "count": 63427, "self": 4.8398097200231405, "children": { "TorchPolicy.evaluate": { "total": 102.65220798295286, "count": 62566, "self": 102.65220798295286 } } }, "workers": { "total": 0.8727052589661071, "count": 63427, "self": 0.0, "children": { "worker_root": { "total": 2150.57345695899, "count": 63427, "is_parallel": true, "self": 870.3855172079502, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017297409999628144, "count": 1, "is_parallel": true, "self": 0.0005389230002492695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011908179997135449, "count": 8, "is_parallel": true, "self": 0.0011908179997135449 } } }, "UnityEnvironment.step": { "total": 0.049008584999910454, "count": 1, "is_parallel": true, "self": 0.0005255049995867012, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005632250001781358, "count": 1, "is_parallel": true, "self": 0.0005632250001781358 }, "communicator.exchange": { "total": 0.04627976100005071, "count": 1, "is_parallel": true, "self": 0.04627976100005071 }, "steps_from_proto": { "total": 0.001640094000094905, "count": 1, "is_parallel": true, "self": 0.000400689000116472, "children": { "_process_rank_one_or_two_observation": { "total": 0.001239404999978433, "count": 8, "is_parallel": true, "self": 0.001239404999978433 } } } } } } }, "UnityEnvironment.step": { "total": 1280.1879397510397, "count": 63426, "is_parallel": true, "self": 32.37392717810894, "children": { "UnityEnvironment._generate_step_input": { "total": 22.90804406896177, "count": 63426, "is_parallel": true, "self": 22.90804406896177 }, "communicator.exchange": { "total": 1130.9939004039602, "count": 63426, "is_parallel": true, "self": 1130.9939004039602 }, "steps_from_proto": { "total": 93.91206810000881, "count": 63426, "is_parallel": true, "self": 20.012300295063824, "children": { "_process_rank_one_or_two_observation": { "total": 73.89976780494499, "count": 507408, "is_parallel": true, "self": 73.89976780494499 } } } } } } } } } } }, "trainer_advance": { "total": 647.619406399943, "count": 63427, "self": 2.7155448008973053, "children": { "process_trajectory": { "total": 105.30106134204334, "count": 63427, "self": 105.04492247304324, "children": { "RLTrainer._checkpoint": { "total": 0.25613886900009675, "count": 2, "self": 0.25613886900009675 } } }, "_update_policy": { "total": 539.6028002570024, "count": 450, "self": 353.4300469520176, "children": { "TorchPPOOptimizer.update": { "total": 186.17275330498478, "count": 22761, "self": 186.17275330498478 } } } } } } }, "trainer_threads": { "total": 1.1140000424347818e-06, "count": 1, "self": 1.1140000424347818e-06 }, "TrainerController._save_models": { "total": 0.10461416699990878, "count": 1, "self": 0.001582849999977043, "children": { "RLTrainer._checkpoint": { "total": 0.10303131699993173, "count": 1, "self": 0.10303131699993173 } } } } } } }