{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1779586672782898, "min": 0.16456937789916992, "max": 1.4253180027008057, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5321.67578125, "min": 4892.318359375, "max": 43238.4453125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999987.0, "min": 29952.0, "max": 2999987.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999987.0, "min": 29952.0, "max": 2999987.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8328723907470703, "min": -0.07972176373004913, "max": 0.8579733371734619, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 247.36309814453125, "min": -19.133222579956055, "max": 265.11376953125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012771681882441044, "min": -0.025285545736551285, "max": 0.5610108375549316, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.793189525604248, "min": -7.813233852386475, "max": 132.95956420898438, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0650420611678523, "min": 0.06291096351369994, "max": 0.07413346289199874, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9105888563499321, "min": 0.5019739824656635, "max": 1.0761149474659333, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015346481514695498, "min": 0.0007967320906727917, "max": 0.016338589652274044, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21485074120573697, "min": 0.011154249269419084, "max": 0.24507884478411068, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4473566604380992e-06, "min": 1.4473566604380992e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0262993246133388e-05, "min": 2.0262993246133388e-05, "max": 0.0040114332628556, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048241904761905, "min": 0.10048241904761905, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067538666666668, "min": 1.3962282666666668, "max": 2.7824947333333343, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.819366285714299e-05, "min": 5.819366285714299e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008147112800000019, "min": 0.0008147112800000019, "max": 0.13372072556, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006155577953904867, "min": 0.005748748779296875, "max": 0.6478404998779297, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08617809414863586, "min": 0.08048248291015625, "max": 4.534883499145508, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 220.2074074074074, "min": 208.47260273972603, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29728.0, "min": 15984.0, "max": 33859.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7649703545150934, "min": -1.0000000521540642, "max": 1.7915273854789668, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 238.2709978595376, "min": -28.81120153516531, "max": 261.56299827992916, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7649703545150934, "min": -1.0000000521540642, "max": 1.7915273854789668, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 238.2709978595376, "min": -28.81120153516531, "max": 261.56299827992916, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014096635815049349, "min": 0.012984605982587896, "max": 13.738744033500552, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9030458350316621, "min": 1.7241441284495522, "max": 219.81990453600883, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679504230", "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": "1679511455" }, "total": 7224.913486271999, "count": 1, "self": 0.5747390009992159, "children": { "run_training.setup": { "total": 0.18553173000009338, "count": 1, "self": 0.18553173000009338 }, "TrainerController.start_learning": { "total": 7224.1532155410005, "count": 1, "self": 4.436710673089692, "children": { "TrainerController._reset_env": { "total": 6.293383216000166, "count": 1, "self": 6.293383216000166 }, "TrainerController.advance": { "total": 7213.323121120911, "count": 194887, "self": 4.574776212712095, "children": { "env_step": { "total": 5326.345967347063, "count": 194887, "self": 4984.043884053048, "children": { "SubprocessEnvManager._take_step": { "total": 339.66303534397775, "count": 194887, "self": 14.827934434942563, "children": { "TorchPolicy.evaluate": { "total": 324.8351009090352, "count": 187561, "self": 324.8351009090352 } } }, "workers": { "total": 2.6390479500382753, "count": 194887, "self": 0.0, "children": { "worker_root": { "total": 7207.996287035747, "count": 194887, "is_parallel": true, "self": 2590.144554819908, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004052168000271195, "count": 1, "is_parallel": true, "self": 0.00219089900065228, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018612689996189147, "count": 8, "is_parallel": true, "self": 0.0018612689996189147 } } }, "UnityEnvironment.step": { "total": 0.049048733999825345, "count": 1, "is_parallel": true, "self": 0.0005467450000651297, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005092940000395174, "count": 1, "is_parallel": true, "self": 0.0005092940000395174 }, "communicator.exchange": { "total": 0.0462991989998045, "count": 1, "is_parallel": true, "self": 0.0462991989998045 }, "steps_from_proto": { "total": 0.0016934959999161947, "count": 1, "is_parallel": true, "self": 0.00037103999966348056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013224560002527141, "count": 8, "is_parallel": true, "self": 0.0013224560002527141 } } } } } } }, "UnityEnvironment.step": { "total": 4617.851732215839, "count": 194886, "is_parallel": true, "self": 94.88996791689533, "children": { "UnityEnvironment._generate_step_input": { "total": 72.21138122306957, "count": 194886, "is_parallel": true, "self": 72.21138122306957 }, "communicator.exchange": { "total": 4154.165759593749, "count": 194886, "is_parallel": true, "self": 4154.165759593749 }, "steps_from_proto": { "total": 296.58462348212606, "count": 194886, "is_parallel": true, "self": 65.2876548203476, "children": { "_process_rank_one_or_two_observation": { "total": 231.29696866177846, "count": 1559088, "is_parallel": true, "self": 231.29696866177846 } } } } } } } } } } }, "trainer_advance": { "total": 1882.4023775611354, "count": 194887, "self": 8.469780868023918, "children": { "process_trajectory": { "total": 373.480020872134, "count": 194887, "self": 372.734858888135, "children": { "RLTrainer._checkpoint": { "total": 0.7451619839989689, "count": 6, "self": 0.7451619839989689 } } }, "_update_policy": { "total": 1500.4525758209775, "count": 1405, "self": 953.0745819321282, "children": { "TorchPPOOptimizer.update": { "total": 547.3779938888492, "count": 68385, "self": 547.3779938888492 } } } } } } }, "trainer_threads": { "total": 9.949999366654083e-07, "count": 1, "self": 9.949999366654083e-07 }, "TrainerController._save_models": { "total": 0.09999953599981382, "count": 1, "self": 0.0015723859996796818, "children": { "RLTrainer._checkpoint": { "total": 0.09842715000013413, "count": 1, "self": 0.09842715000013413 } } } } } } }