{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3365216553211212, "min": 0.3365216553211212, "max": 1.4484621286392212, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10036.421875, "min": 10036.421875, "max": 43940.546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.640660285949707, "min": -0.12196584045886993, "max": 0.6657708287239075, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 184.51016235351562, "min": -29.393768310546875, "max": 188.41314697265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.08293252438306808, "min": -0.024033155292272568, "max": 0.24586895108222961, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 23.884567260742188, "min": -6.681217193603516, "max": 59.254417419433594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07094222832321455, "min": 0.06581010895358654, "max": 0.07478215206697948, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9931911965250038, "min": 0.5234750644688564, "max": 1.0615083338788656, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015168242004403424, "min": 0.0002043031913867869, "max": 0.017124580906915054, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21235538806164794, "min": 0.0022473351052546557, "max": 0.23974413269681075, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4101189585642865e-06, "min": 7.4101189585642865e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010374166541990002, "min": 0.00010374166541990002, "max": 0.003507135230955, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247000714285714, "min": 0.10247000714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345801, "min": 1.3886848, "max": 2.569045, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025675371357142864, "min": 0.00025675371357142864, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035945519900000013, "min": 0.0035945519900000013, "max": 0.1169275955, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01268954761326313, "min": 0.01268954761326313, "max": 0.4171176552772522, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17765367031097412, "min": 0.17765367031097412, "max": 2.91982364654541, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 289.77142857142854, "min": 289.70588235294116, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30426.0, "min": 15984.0, "max": 32640.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.653196210709383, "min": -1.0000000521540642, "max": 1.6765957714695678, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.2387983351946, "min": -31.998001664876938, "max": 175.2387983351946, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.653196210709383, "min": -1.0000000521540642, "max": 1.6765957714695678, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.2387983351946, "min": -31.998001664876938, "max": 175.2387983351946, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038323491612967664, "min": 0.038323491612967664, "max": 7.935516747646034, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.062290110974573, "min": 3.767997092596488, "max": 126.96826796233654, "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": "1679931876", "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": "1679934159" }, "total": 2283.173215607, "count": 1, "self": 0.6915045870005088, "children": { "run_training.setup": { "total": 0.17707243000000972, "count": 1, "self": 0.17707243000000972 }, "TrainerController.start_learning": { "total": 2282.3046385899997, "count": 1, "self": 1.5352413240184433, "children": { "TrainerController._reset_env": { "total": 7.0850011629999585, "count": 1, "self": 7.0850011629999585 }, "TrainerController.advance": { "total": 2273.5398544489813, "count": 64031, "self": 1.653480109972861, "children": { "env_step": { "total": 1626.5293838810228, "count": 64031, "self": 1509.1345152799734, "children": { "SubprocessEnvManager._take_step": { "total": 116.47823860406714, "count": 64031, "self": 4.942899063056643, "children": { "TorchPolicy.evaluate": { "total": 111.5353395410105, "count": 62560, "self": 111.5353395410105 } } }, "workers": { "total": 0.9166299969822944, "count": 64031, "self": 0.0, "children": { "worker_root": { "total": 2277.029340261, "count": 64031, "is_parallel": true, "self": 892.9101473959754, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024416360000145687, "count": 1, "is_parallel": true, "self": 0.0006283860001872199, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018132499998273488, "count": 8, "is_parallel": true, "self": 0.0018132499998273488 } } }, "UnityEnvironment.step": { "total": 0.05208552099998087, "count": 1, "is_parallel": true, "self": 0.0005260759999146103, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005030760000295231, "count": 1, "is_parallel": true, "self": 0.0005030760000295231 }, "communicator.exchange": { "total": 0.04932225700002846, "count": 1, "is_parallel": true, "self": 0.04932225700002846 }, "steps_from_proto": { "total": 0.001734112000008281, "count": 1, "is_parallel": true, "self": 0.0003920039999911751, "children": { "_process_rank_one_or_two_observation": { "total": 0.001342108000017106, "count": 8, "is_parallel": true, "self": 0.001342108000017106 } } } } } } }, "UnityEnvironment.step": { "total": 1384.1191928650246, "count": 64030, "is_parallel": true, "self": 31.985642425074275, "children": { "UnityEnvironment._generate_step_input": { "total": 24.45032347900616, "count": 64030, "is_parallel": true, "self": 24.45032347900616 }, "communicator.exchange": { "total": 1229.1724382369603, "count": 64030, "is_parallel": true, "self": 1229.1724382369603 }, "steps_from_proto": { "total": 98.51078872398404, "count": 64030, "is_parallel": true, "self": 21.628850915974454, "children": { "_process_rank_one_or_two_observation": { "total": 76.88193780800958, "count": 512240, "is_parallel": true, "self": 76.88193780800958 } } } } } } } } } } }, "trainer_advance": { "total": 645.3569904579855, "count": 64031, "self": 2.792628730926026, "children": { "process_trajectory": { "total": 125.25838341505585, "count": 64031, "self": 124.9977282190556, "children": { "RLTrainer._checkpoint": { "total": 0.26065519600024345, "count": 2, "self": 0.26065519600024345 } } }, "_update_policy": { "total": 517.3059783120036, "count": 452, "self": 329.77821099598043, "children": { "TorchPPOOptimizer.update": { "total": 187.5277673160232, "count": 22845, "self": 187.5277673160232 } } } } } } }, "trainer_threads": { "total": 1.4199999895936344e-06, "count": 1, "self": 1.4199999895936344e-06 }, "TrainerController._save_models": { "total": 0.1445402340000328, "count": 1, "self": 0.0018419319999338768, "children": { "RLTrainer._checkpoint": { "total": 0.14269830200009892, "count": 1, "self": 0.14269830200009892 } } } } } } }