{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6744004487991333, "min": 0.6279477477073669, "max": 1.4389331340789795, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 20242.8046875, "min": 18808.291015625, "max": 43651.4765625, "count": 16 }, "Pyramids.Step.mean": { "value": 479949.0, "min": 29911.0, "max": 479949.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479949.0, "min": 29911.0, "max": 479949.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07185470312833786, "min": -0.17655961215496063, "max": -0.04350561648607254, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.388837814331055, "min": -41.844627380371094, "max": -10.484853744506836, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025986438617110252, "min": 0.025986438617110252, "max": 0.5183269381523132, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.288718223571777, "min": 6.288718223571777, "max": 122.84349060058594, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0664786800839162, "min": 0.0660214240548484, "max": 0.07667070973129948, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9971802012587432, "min": 0.5366949681190963, "max": 0.9971802012587432, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0010628796029239765, "min": 8.687094145246701e-05, "max": 0.015348110088629397, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.015943194043859646, "min": 0.0011293222388820711, "max": 0.10743677062040578, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.1031012989693328e-05, "min": 2.1031012989693328e-05, "max": 0.00029046934603402854, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0003154651948453999, "min": 0.0003154651948453999, "max": 0.0030081042972986, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1070103066666667, "min": 0.1070103066666667, "max": 0.19682311428571433, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.6051546000000003, "min": 1.3777618000000003, "max": 2.1504756, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.000710329636, "min": 0.000710329636, "max": 0.009682629117142858, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.010654944539999999, "min": 0.010654944539999999, "max": 0.10027986986000001, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.023155469447374344, "min": 0.023155469447374344, "max": 0.5172693729400635, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.34733203053474426, "min": 0.34733203053474426, "max": 3.6208856105804443, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 985.6875, "min": 921.3714285714286, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31542.0, "min": 16582.0, "max": 32633.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8613000512123108, "min": -1.0000000521540642, "max": -0.6297937964554876, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.561601638793945, "min": -31.00000161677599, "max": -14.598000824451447, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8613000512123108, "min": -1.0000000521540642, "max": -0.6297937964554876, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.561601638793945, "min": -31.00000161677599, "max": -14.598000824451447, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.23722474297392182, "min": 0.23722474297392182, "max": 10.942024974262013, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 7.591191775165498, "min": 7.591191775165498, "max": 186.01442456245422, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1660495718", "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": "1660496796" }, "total": 1077.3808963239999, "count": 1, "self": 0.5849955929998032, "children": { "run_training.setup": { "total": 0.045422839000025306, "count": 1, "self": 0.045422839000025306 }, "TrainerController.start_learning": { "total": 1076.750477892, "count": 1, "self": 0.8704222589813071, "children": { "TrainerController._reset_env": { "total": 10.453357380000057, "count": 1, "self": 10.453357380000057 }, "TrainerController.advance": { "total": 1065.3259633640187, "count": 31483, "self": 0.9101491740116217, "children": { "env_step": { "total": 676.3301160650037, "count": 31483, "self": 613.3853840809991, "children": { "SubprocessEnvManager._take_step": { "total": 62.487276469006474, "count": 31483, "self": 2.724464295002008, "children": { "TorchPolicy.evaluate": { "total": 59.762812174004466, "count": 31320, "self": 19.728655800021443, "children": { "TorchPolicy.sample_actions": { "total": 40.03415637398302, "count": 31320, "self": 40.03415637398302 } } } } }, "workers": { "total": 0.4574555149981734, "count": 31483, "self": 0.0, "children": { "worker_root": { "total": 1074.416256594, "count": 31483, "is_parallel": true, "self": 521.7141687980189, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006045080000035341, "count": 1, "is_parallel": true, "self": 0.004609021999954166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014360580000811751, "count": 8, "is_parallel": true, "self": 0.0014360580000811751 } } }, "UnityEnvironment.step": { "total": 0.06217732300001444, "count": 1, "is_parallel": true, "self": 0.0005548049999788418, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005626739999797792, "count": 1, "is_parallel": true, "self": 0.0005626739999797792 }, "communicator.exchange": { "total": 0.059063289000050645, "count": 1, "is_parallel": true, "self": 0.059063289000050645 }, "steps_from_proto": { "total": 0.0019965550000051735, "count": 1, "is_parallel": true, "self": 0.0005149029999529375, "children": { "_process_rank_one_or_two_observation": { "total": 0.001481652000052236, "count": 8, "is_parallel": true, "self": 0.001481652000052236 } } } } } } }, "UnityEnvironment.step": { "total": 552.7020877959811, "count": 31482, "is_parallel": true, "self": 15.415234653966536, "children": { "UnityEnvironment._generate_step_input": { "total": 13.952503467011184, "count": 31482, "is_parallel": true, "self": 13.952503467011184 }, "communicator.exchange": { "total": 468.87459622200686, "count": 31482, "is_parallel": true, "self": 468.87459622200686 }, "steps_from_proto": { "total": 54.45975345299655, "count": 31482, "is_parallel": true, "self": 13.876780016961675, "children": { "_process_rank_one_or_two_observation": { "total": 40.58297343603488, "count": 251856, "is_parallel": true, "self": 40.58297343603488 } } } } } } } } } } }, "trainer_advance": { "total": 388.08569812500343, "count": 31483, "self": 1.3359164990207546, "children": { "process_trajectory": { "total": 91.49801288698382, "count": 31483, "self": 91.38036461398383, "children": { "RLTrainer._checkpoint": { "total": 0.11764827299998615, "count": 1, "self": 0.11764827299998615 } } }, "_update_policy": { "total": 295.25176873899886, "count": 209, "self": 117.03617135099762, "children": { "TorchPPOOptimizer.update": { "total": 178.21559738800124, "count": 11406, "self": 178.21559738800124 } } } } } } }, "trainer_threads": { "total": 1.1530000847415067e-06, "count": 1, "self": 1.1530000847415067e-06 }, "TrainerController._save_models": { "total": 0.10073373599993829, "count": 1, "self": 0.0016695009999239119, "children": { "RLTrainer._checkpoint": { "total": 0.09906423500001438, "count": 1, "self": 0.09906423500001438 } } } } } } }