{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4499475359916687, "min": 0.4499475359916687, "max": 1.5457075834274292, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13455.2314453125, "min": 13455.2314453125, "max": 46890.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4569282829761505, "min": -0.11926969885826111, "max": 0.5552018880844116, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.74142456054688, "min": -28.98253631591797, "max": 153.2357177734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03721953183412552, "min": -0.008403838612139225, "max": 0.23590321838855743, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.160932540893555, "min": -2.2606325149536133, "max": 55.909061431884766, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07088143168754565, "min": 0.06712802966295787, "max": 0.07273202882801046, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0632214753131848, "min": 0.4900225909014002, "max": 1.0721480116869013, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015250895472127013, "min": 0.0003278082768057267, "max": 0.015250895472127013, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2287634320819052, "min": 0.00295027449125154, "max": 0.2287634320819052, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.458517513860003e-06, "min": 7.458517513860003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011187776270790004, "min": 0.00011187776270790004, "max": 0.003507145130951699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248614000000003, "min": 0.10248614000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372921000000004, "min": 1.3691136000000002, "max": 2.5690483000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002583653860000002, "min": 0.0002583653860000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038754807900000026, "min": 0.0038754807900000026, "max": 0.11692792516999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00885879434645176, "min": 0.00885879434645176, "max": 0.2943384647369385, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13288190960884094, "min": 0.12933258712291718, "max": 2.0603692531585693, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 376.0632911392405, "min": 360.56626506024094, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29709.0, "min": 15984.0, "max": 33960.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4973113796190372, "min": -1.0000000521540642, "max": 1.6142118787836461, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.28759898990393, "min": -32.000001668930054, "max": 135.59379781782627, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4973113796190372, "min": -1.0000000521540642, "max": 1.6142118787836461, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.28759898990393, "min": -32.000001668930054, "max": 135.59379781782627, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03474338145002272, "min": 0.03474338145002272, "max": 5.996169783174992, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7447271345517947, "min": 2.7447271345517947, "max": 95.93871653079987, "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": "1697067423", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697069594" }, "total": 2171.0152228360002, "count": 1, "self": 0.4763712450003368, "children": { "run_training.setup": { "total": 0.04263445900005536, "count": 1, "self": 0.04263445900005536 }, "TrainerController.start_learning": { "total": 2170.496217132, "count": 1, "self": 1.307254544947682, "children": { "TrainerController._reset_env": { "total": 3.055690436999612, "count": 1, "self": 3.055690436999612 }, "TrainerController.advance": { "total": 2166.053219009052, "count": 63595, "self": 1.3317053889818453, "children": { "env_step": { "total": 1545.2735498650154, "count": 63595, "self": 1423.6859163048744, "children": { "SubprocessEnvManager._take_step": { "total": 120.80563918602047, "count": 63595, "self": 4.613375374005045, "children": { "TorchPolicy.evaluate": { "total": 116.19226381201543, "count": 62556, "self": 116.19226381201543 } } }, "workers": { "total": 0.7819943741205861, "count": 63595, "self": 0.0, "children": { "worker_root": { "total": 2166.0337353290574, "count": 63595, "is_parallel": true, "self": 856.7613455719952, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018361289999120345, "count": 1, "is_parallel": true, "self": 0.0006013289998918481, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012348000000201864, "count": 8, "is_parallel": true, "self": 0.0012348000000201864 } } }, "UnityEnvironment.step": { "total": 0.09753808599998592, "count": 1, "is_parallel": true, "self": 0.0005918260003454634, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004708559999926365, "count": 1, "is_parallel": true, "self": 0.0004708559999926365 }, "communicator.exchange": { "total": 0.09485839699982535, "count": 1, "is_parallel": true, "self": 0.09485839699982535 }, "steps_from_proto": { "total": 0.001617006999822479, "count": 1, "is_parallel": true, "self": 0.0003822150010819314, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012347919987405476, "count": 8, "is_parallel": true, "self": 0.0012347919987405476 } } } } } } }, "UnityEnvironment.step": { "total": 1309.2723897570622, "count": 63594, "is_parallel": true, "self": 33.883496454186115, "children": { "UnityEnvironment._generate_step_input": { "total": 23.262082721974366, "count": 63594, "is_parallel": true, "self": 23.262082721974366 }, "communicator.exchange": { "total": 1156.6024991299646, "count": 63594, "is_parallel": true, "self": 1156.6024991299646 }, "steps_from_proto": { "total": 95.52431145093715, "count": 63594, "is_parallel": true, "self": 18.74993117291706, "children": { "_process_rank_one_or_two_observation": { "total": 76.77438027802009, "count": 508752, "is_parallel": true, "self": 76.77438027802009 } } } } } } } } } } }, "trainer_advance": { "total": 619.4479637550548, "count": 63595, "self": 2.508581299119669, "children": { "process_trajectory": { "total": 115.8541132819405, "count": 63595, "self": 115.67944414694057, "children": { "RLTrainer._checkpoint": { "total": 0.17466913499993098, "count": 2, "self": 0.17466913499993098 } } }, "_update_policy": { "total": 501.0852691739947, "count": 441, "self": 300.7676622200561, "children": { "TorchPPOOptimizer.update": { "total": 200.3176069539386, "count": 22845, "self": 200.3176069539386 } } } } } } }, "trainer_threads": { "total": 1.0630001270328648e-06, "count": 1, "self": 1.0630001270328648e-06 }, "TrainerController._save_models": { "total": 0.08005207800033531, "count": 1, "self": 0.001439779000065755, "children": { "RLTrainer._checkpoint": { "total": 0.07861229900026956, "count": 1, "self": 0.07861229900026956 } } } } } } }