{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39257508516311646, "min": 0.39257508516311646, "max": 1.4087611436843872, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11808.658203125, "min": 11766.6416015625, "max": 42736.1796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29981.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29981.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5082176327705383, "min": -0.1057649478316307, "max": 0.5082176327705383, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.2516326904297, "min": -25.48935317993164, "max": 139.2516326904297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02359437756240368, "min": -0.00028974772430956364, "max": 0.2931281328201294, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.464859485626221, "min": -0.07591390609741211, "max": 69.76449584960938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06404066440882161, "min": 0.06404066440882161, "max": 0.07368135447004101, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8965693017235026, "min": 0.5688402471504965, "max": 1.0904893651022576, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01550512508471175, "min": 0.0003220662831544425, "max": 0.016655293391716335, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2170717511859645, "min": 0.0035427291146988677, "max": 0.2331741074840287, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.58268318675714e-06, "min": 7.58268318675714e-06, "max": 0.00029485113921628753, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010615756461459995, "min": 0.00010615756461459995, "max": 0.0033316752894416, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252752857142856, "min": 0.10252752857142856, "max": 0.1982837125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353854, "min": 1.4353854, "max": 2.4442334, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026250010428571416, "min": 0.00026250010428571416, "max": 0.009828542878749999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003675001459999998, "min": 0.003675001459999998, "max": 0.11106478416000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011020584031939507, "min": 0.011020584031939507, "max": 0.3701419532299042, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1542881727218628, "min": 0.1542881727218628, "max": 2.9611356258392334, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 367.05263157894734, "min": 367.0238095238095, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27896.0, "min": 16396.0, "max": 33304.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.503716866304348, "min": -0.9999724657371126, "max": 1.5149476035010248, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.7861987054348, "min": -31.998401656746864, "max": 127.25559869408607, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.503716866304348, "min": -0.9999724657371126, "max": 1.5149476035010248, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.7861987054348, "min": -31.998401656746864, "max": 127.25559869408607, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04155655826465378, "min": 0.04155655826465378, "max": 7.7459842194529145, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.199854986378341, "min": 3.199854986378341, "max": 131.68173173069954, "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": "1657812586", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1657814544" }, "total": 1958.4482300920001, "count": 1, "self": 0.4941803610001898, "children": { "run_training.setup": { "total": 0.040768194000065705, "count": 1, "self": 0.040768194000065705 }, "TrainerController.start_learning": { "total": 1957.9132815369999, "count": 1, "self": 1.3127023560000453, "children": { "TrainerController._reset_env": { "total": 9.742710181000007, "count": 1, "self": 9.742710181000007 }, "TrainerController.advance": { "total": 1946.7639129889992, "count": 63525, "self": 1.4336701729605466, "children": { "env_step": { "total": 1240.7290249590008, "count": 63525, "self": 1137.8875941429037, "children": { "SubprocessEnvManager._take_step": { "total": 102.13995725406312, "count": 63525, "self": 4.657287240025653, "children": { "TorchPolicy.evaluate": { "total": 97.48267001403747, "count": 62578, "self": 33.678508270083285, "children": { "TorchPolicy.sample_actions": { "total": 63.80416174395418, "count": 62578, "self": 63.80416174395418 } } } } }, "workers": { "total": 0.7014735620340389, "count": 63525, "self": 0.0, "children": { "worker_root": { "total": 1954.1475096050424, "count": 63525, "is_parallel": true, "self": 914.3439483840159, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00545921500008717, "count": 1, "is_parallel": true, "self": 0.0039989220000506975, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014602930000364722, "count": 8, "is_parallel": true, "self": 0.0014602930000364722 } } }, "UnityEnvironment.step": { "total": 0.049674761000005674, "count": 1, "is_parallel": true, "self": 0.0005410940000274422, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006444680000186054, "count": 1, "is_parallel": true, "self": 0.0006444680000186054 }, "communicator.exchange": { "total": 0.046706916999937675, "count": 1, "is_parallel": true, "self": 0.046706916999937675 }, "steps_from_proto": { "total": 0.0017822820000219508, "count": 1, "is_parallel": true, "self": 0.00047354999992421654, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013087320000977343, "count": 8, "is_parallel": true, "self": 0.0013087320000977343 } } } } } } }, "UnityEnvironment.step": { "total": 1039.8035612210265, "count": 63524, "is_parallel": true, "self": 27.438827749088432, "children": { "UnityEnvironment._generate_step_input": { "total": 22.856510588954848, "count": 63524, "is_parallel": true, "self": 22.856510588954848 }, "communicator.exchange": { "total": 898.2329030119697, "count": 63524, "is_parallel": true, "self": 898.2329030119697 }, "steps_from_proto": { "total": 91.2753198710135, "count": 63524, "is_parallel": true, "self": 22.278655631937, "children": { "_process_rank_one_or_two_observation": { "total": 68.9966642390765, "count": 508192, "is_parallel": true, "self": 68.9966642390765 } } } } } } } } } } }, "trainer_advance": { "total": 704.6012178570378, "count": 63525, "self": 2.4058228190177715, "children": { "process_trajectory": { "total": 159.03486191101808, "count": 63525, "self": 158.83881118101806, "children": { "RLTrainer._checkpoint": { "total": 0.1960507300000245, "count": 2, "self": 0.1960507300000245 } } }, "_update_policy": { "total": 543.1605331270019, "count": 450, "self": 216.17769340999018, "children": { "TorchPPOOptimizer.update": { "total": 326.98283971701176, "count": 22782, "self": 326.98283971701176 } } } } } } }, "trainer_threads": { "total": 1.0380003914178815e-06, "count": 1, "self": 1.0380003914178815e-06 }, "TrainerController._save_models": { "total": 0.09395497300010902, "count": 1, "self": 0.0016927669998949568, "children": { "RLTrainer._checkpoint": { "total": 0.09226220600021406, "count": 1, "self": 0.09226220600021406 } } } } } } }