{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44644874334335327, "min": 0.3676552474498749, "max": 1.5143574476242065, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13500.6103515625, "min": 10988.48046875, "max": 45939.546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.023671751841902733, "min": -0.12484000623226166, "max": 0.020460186526179314, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -5.823250770568848, "min": -29.96160125732422, "max": 5.033205986022949, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015064789913594723, "min": 0.007779942825436592, "max": 0.2985401451587677, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7059383392333984, "min": 1.8905260562896729, "max": 70.75401306152344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06987025700126206, "min": 0.06308633619039994, "max": 0.07291689615127399, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.978183598017669, "min": 0.48714370067945906, "max": 1.020836546117836, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004308005329838892, "min": 0.0003557545800103571, "max": 0.006350466536295944, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06031207461774449, "min": 0.004269054960124285, "max": 0.08134268601649333, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.26903329130714e-06, "min": 7.26903329130714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010176646607829997, "min": 0.00010176646607829997, "max": 0.0032251465249512, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242297857142858, "min": 0.10242297857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339217000000002, "min": 1.3886848, "max": 2.3591381, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002520555592857142, "min": 0.0002520555592857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003528777829999999, "min": 0.003528777829999999, "max": 0.10751737512000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013996501453220844, "min": 0.013996501453220844, "max": 0.33533814549446106, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19595101475715637, "min": 0.19595101475715637, "max": 2.34736704826355, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 858.78125, "min": 845.6, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27481.0, "min": 15984.0, "max": 33275.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.2573151940649206, "min": -1.0000000521540642, "max": -0.10974122255164034, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -8.49140140414238, "min": -31.998001664876938, "max": -3.7312015667557716, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.2573151940649206, "min": -1.0000000521540642, "max": -0.10974122255164034, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -8.49140140414238, "min": -31.998001664876938, "max": -3.7312015667557716, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12426557639529082, "min": 0.12426557639529082, "max": 6.772108065895736, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.100764021044597, "min": 4.100764021044597, "max": 108.35372905433178, "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": "1721085353", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721087429" }, "total": 2076.213223665, "count": 1, "self": 0.7710439369998312, "children": { "run_training.setup": { "total": 0.05299816499996268, "count": 1, "self": 0.05299816499996268 }, "TrainerController.start_learning": { "total": 2075.389181563, "count": 1, "self": 1.3396246060306112, "children": { "TrainerController._reset_env": { "total": 3.0947472789999892, "count": 1, "self": 3.0947472789999892 }, "TrainerController.advance": { "total": 2070.816000836969, "count": 63084, "self": 1.4424802599965005, "children": { "env_step": { "total": 1431.9340216029757, "count": 63084, "self": 1295.174599659891, "children": { "SubprocessEnvManager._take_step": { "total": 135.94093703706358, "count": 63084, "self": 4.702591132075781, "children": { "TorchPolicy.evaluate": { "total": 131.2383459049878, "count": 62560, "self": 131.2383459049878 } } }, "workers": { "total": 0.8184849060210126, "count": 63084, "self": 0.0, "children": { "worker_root": { "total": 2070.184102519953, "count": 63084, "is_parallel": true, "self": 895.4354172239314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0074982170000339465, "count": 1, "is_parallel": true, "self": 0.006018389000246316, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014798279997876307, "count": 8, "is_parallel": true, "self": 0.0014798279997876307 } } }, "UnityEnvironment.step": { "total": 0.046383439000010185, "count": 1, "is_parallel": true, "self": 0.0006040429999529806, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000494645000003402, "count": 1, "is_parallel": true, "self": 0.000494645000003402 }, "communicator.exchange": { "total": 0.04369731300005242, "count": 1, "is_parallel": true, "self": 0.04369731300005242 }, "steps_from_proto": { "total": 0.0015874380000013844, "count": 1, "is_parallel": true, "self": 0.00033080699995480245, "children": { "_process_rank_one_or_two_observation": { "total": 0.001256631000046582, "count": 8, "is_parallel": true, "self": 0.001256631000046582 } } } } } } }, "UnityEnvironment.step": { "total": 1174.7486852960214, "count": 63083, "is_parallel": true, "self": 33.69908443803752, "children": { "UnityEnvironment._generate_step_input": { "total": 24.340683978965558, "count": 63083, "is_parallel": true, "self": 24.340683978965558 }, "communicator.exchange": { "total": 1016.8807618280055, "count": 63083, "is_parallel": true, "self": 1016.8807618280055 }, "steps_from_proto": { "total": 99.82815505101269, "count": 63083, "is_parallel": true, "self": 20.340872805867775, "children": { "_process_rank_one_or_two_observation": { "total": 79.48728224514491, "count": 504664, "is_parallel": true, "self": 79.48728224514491 } } } } } } } } } } }, "trainer_advance": { "total": 637.439498973997, "count": 63084, "self": 2.432558802996823, "children": { "process_trajectory": { "total": 127.38925482500076, "count": 63084, "self": 127.08381082400047, "children": { "RLTrainer._checkpoint": { "total": 0.30544400100029634, "count": 2, "self": 0.30544400100029634 } } }, "_update_policy": { "total": 507.61768534599946, "count": 436, "self": 302.58717557801504, "children": { "TorchPPOOptimizer.update": { "total": 205.03050976798443, "count": 22776, "self": 205.03050976798443 } } } } } } }, "trainer_threads": { "total": 1.2940004125994164e-06, "count": 1, "self": 1.2940004125994164e-06 }, "TrainerController._save_models": { "total": 0.13880754699994213, "count": 1, "self": 0.002354190000005474, "children": { "RLTrainer._checkpoint": { "total": 0.13645335699993666, "count": 1, "self": 0.13645335699993666 } } } } } } }