{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.529485821723938, "min": 0.4993588626384735, "max": 1.4616461992263794, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15926.93359375, "min": 15036.6943359375, "max": 44340.5, "count": 33 }, "Pyramids.Step.mean": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4258022606372833, "min": -0.11910755932331085, "max": 0.4258022606372833, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.11500549316406, "min": -28.70492172241211, "max": 114.11500549316406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012714996002614498, "min": -0.007144283503293991, "max": 0.4556998014450073, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.407618999481201, "min": -1.857513666152954, "max": 108.0008544921875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06884660100103264, "min": 0.06531196481124166, "max": 0.0740321751673597, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.963852414014457, "min": 0.49166428222305586, "max": 1.037727091414055, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015690361774994974, "min": 0.00019108918636427351, "max": 0.016808480010601087, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21966506484992962, "min": 0.0022930702363712823, "max": 0.2353187201484152, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.644204594821426e-06, "min": 7.644204594821426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010701886432749996, "min": 0.00010701886432749996, "max": 0.0029056149314618, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254803571428571, "min": 0.10254803571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356725, "min": 1.3691136000000002, "max": 2.3600056, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026454876785714275, "min": 0.00026454876785714275, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037036827499999985, "min": 0.0037036827499999985, "max": 0.09688696617999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012615271843969822, "min": 0.012615271843969822, "max": 0.5443219542503357, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17661380767822266, "min": 0.17661380767822266, "max": 3.810253620147705, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 408.5, "min": 408.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28595.0, "min": 15984.0, "max": 32738.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5343285558479174, "min": -1.0000000521540642, "max": 1.5343285558479174, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 107.40299890935421, "min": -32.000001668930054, "max": 107.40299890935421, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5343285558479174, "min": -1.0000000521540642, "max": 1.5343285558479174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 107.40299890935421, "min": -32.000001668930054, "max": 107.40299890935421, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05344877265535095, "min": 0.05344877265535095, "max": 11.804602368734777, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.741414085874567, "min": 3.741414085874567, "max": 188.87363789975643, "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": "1680000092", "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": "1680002389" }, "total": 2297.487206656, "count": 1, "self": 0.48180778799996915, "children": { "run_training.setup": { "total": 0.16622535200008315, "count": 1, "self": 0.16622535200008315 }, "TrainerController.start_learning": { "total": 2296.839173516, "count": 1, "self": 1.627811249982642, "children": { "TrainerController._reset_env": { "total": 7.029436982000107, "count": 1, "self": 7.029436982000107 }, "TrainerController.advance": { "total": 2288.082484776017, "count": 63444, "self": 1.8137734400579575, "children": { "env_step": { "total": 1621.8420421009735, "count": 63444, "self": 1493.7257289928943, "children": { "SubprocessEnvManager._take_step": { "total": 127.10540279005272, "count": 63444, "self": 5.42739394002092, "children": { "TorchPolicy.evaluate": { "total": 121.6780088500318, "count": 62550, "self": 121.6780088500318 } } }, "workers": { "total": 1.01091031802639, "count": 63444, "self": 0.0, "children": { "worker_root": { "total": 2290.780259015002, "count": 63444, "is_parallel": true, "self": 929.3792146330138, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028713919998608617, "count": 1, "is_parallel": true, "self": 0.0009419079995041102, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019294840003567515, "count": 8, "is_parallel": true, "self": 0.0019294840003567515 } } }, "UnityEnvironment.step": { "total": 0.048371620000125404, "count": 1, "is_parallel": true, "self": 0.0005384570004025591, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005225019999670621, "count": 1, "is_parallel": true, "self": 0.0005225019999670621 }, "communicator.exchange": { "total": 0.0454949149998356, "count": 1, "is_parallel": true, "self": 0.0454949149998356 }, "steps_from_proto": { "total": 0.001815745999920182, "count": 1, "is_parallel": true, "self": 0.0004092859996944753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014064600002257066, "count": 8, "is_parallel": true, "self": 0.0014064600002257066 } } } } } } }, "UnityEnvironment.step": { "total": 1361.401044381988, "count": 63443, "is_parallel": true, "self": 33.86037188601222, "children": { "UnityEnvironment._generate_step_input": { "total": 25.819979234004677, "count": 63443, "is_parallel": true, "self": 25.819979234004677 }, "communicator.exchange": { "total": 1197.5908966179738, "count": 63443, "is_parallel": true, "self": 1197.5908966179738 }, "steps_from_proto": { "total": 104.12979664399722, "count": 63443, "is_parallel": true, "self": 23.011589422063707, "children": { "_process_rank_one_or_two_observation": { "total": 81.11820722193352, "count": 507544, "is_parallel": true, "self": 81.11820722193352 } } } } } } } } } } }, "trainer_advance": { "total": 664.4266692349854, "count": 63444, "self": 2.8843581470086974, "children": { "process_trajectory": { "total": 131.28870298897573, "count": 63444, "self": 131.0153982869756, "children": { "RLTrainer._checkpoint": { "total": 0.27330470200013224, "count": 2, "self": 0.27330470200013224 } } }, "_update_policy": { "total": 530.253608099001, "count": 434, "self": 336.2344478450418, "children": { "TorchPPOOptimizer.update": { "total": 194.01916025395917, "count": 22860, "self": 194.01916025395917 } } } } } } }, "trainer_threads": { "total": 9.890000001178123e-07, "count": 1, "self": 9.890000001178123e-07 }, "TrainerController._save_models": { "total": 0.09943951900004322, "count": 1, "self": 0.0019331210000927967, "children": { "RLTrainer._checkpoint": { "total": 0.09750639799995042, "count": 1, "self": 0.09750639799995042 } } } } } } }