{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5273536443710327, "min": 0.5273536443710327, "max": 1.4829846620559692, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15694.0439453125, "min": 15694.0439453125, "max": 44987.82421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.38594213128089905, "min": -0.10947687178850174, "max": 0.3861941397190094, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.11683654785156, "min": -25.94601821899414, "max": 104.27241516113281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.22505539655685425, "min": -0.19542889297008514, "max": 0.36025846004486084, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 58.964515686035156, "min": -51.202369689941406, "max": 87.6873779296875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07016908678564333, "min": 0.06435269770449649, "max": 0.07208294852957828, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9823672149990066, "min": 0.4897397064711582, "max": 1.0670874542459692, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01565790699706191, "min": 0.0002835766989385282, "max": 0.030488974095099253, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21921069795886675, "min": 0.0036864970862008667, "max": 0.4268456373313895, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.237340444728572e-06, "min": 7.237340444728572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001013227662262, "min": 0.0001013227662262, "max": 0.0036332551889149997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241241428571432, "min": 0.10241241428571432, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337738000000004, "min": 1.3886848, "max": 2.611085, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002510001871428572, "min": 0.0002510001871428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00351400262, "min": 0.00351400262, "max": 0.12112739150000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01394361536949873, "min": 0.013774542137980461, "max": 0.5705505013465881, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19521062076091766, "min": 0.19521062076091766, "max": 3.9938535690307617, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 451.8709677419355, "min": 451.8709677419355, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28016.0, "min": 15984.0, "max": 32211.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4190451363402028, "min": -1.0000000521540642, "max": 1.4190451363402028, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.98079845309258, "min": -29.92300160974264, "max": 87.98079845309258, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4190451363402028, "min": -1.0000000521540642, "max": 1.4190451363402028, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.98079845309258, "min": -29.92300160974264, "max": 87.98079845309258, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0655380303587956, "min": 0.0655380303587956, "max": 10.456163081340492, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.063357882245327, "min": 4.063357882245327, "max": 167.29860930144787, "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": "1701011214", "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=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701013434" }, "total": 2220.5003975689997, "count": 1, "self": 0.8071717769994393, "children": { "run_training.setup": { "total": 0.056438484999944194, "count": 1, "self": 0.056438484999944194 }, "TrainerController.start_learning": { "total": 2219.6367873070003, "count": 1, "self": 1.422737879968281, "children": { "TrainerController._reset_env": { "total": 3.7770889000000807, "count": 1, "self": 3.7770889000000807 }, "TrainerController.advance": { "total": 2214.3246506600317, "count": 63506, "self": 1.5146912170694122, "children": { "env_step": { "total": 1536.6920278759842, "count": 63506, "self": 1398.256106146963, "children": { "SubprocessEnvManager._take_step": { "total": 137.5384910450025, "count": 63506, "self": 4.892661445056547, "children": { "TorchPolicy.evaluate": { "total": 132.64582959994596, "count": 62573, "self": 132.64582959994596 } } }, "workers": { "total": 0.8974306840186728, "count": 63506, "self": 0.0, "children": { "worker_root": { "total": 2214.8482033500754, "count": 63506, "is_parallel": true, "self": 940.1061948861575, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001959534999969037, "count": 1, "is_parallel": true, "self": 0.0006462009994265827, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013133340005424543, "count": 8, "is_parallel": true, "self": 0.0013133340005424543 } } }, "UnityEnvironment.step": { "total": 0.0874788419998822, "count": 1, "is_parallel": true, "self": 0.0005728710000312276, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048256399986712495, "count": 1, "is_parallel": true, "self": 0.00048256399986712495 }, "communicator.exchange": { "total": 0.08479802500005462, "count": 1, "is_parallel": true, "self": 0.08479802500005462 }, "steps_from_proto": { "total": 0.0016253819999292318, "count": 1, "is_parallel": true, "self": 0.00035083900002064183, "children": { "_process_rank_one_or_two_observation": { "total": 0.00127454299990859, "count": 8, "is_parallel": true, "self": 0.00127454299990859 } } } } } } }, "UnityEnvironment.step": { "total": 1274.742008463918, "count": 63505, "is_parallel": true, "self": 34.56873266592106, "children": { "UnityEnvironment._generate_step_input": { "total": 23.44192054796281, "count": 63505, "is_parallel": true, "self": 23.44192054796281 }, "communicator.exchange": { "total": 1119.855529989066, "count": 63505, "is_parallel": true, "self": 1119.855529989066 }, "steps_from_proto": { "total": 96.87582526096799, "count": 63505, "is_parallel": true, "self": 19.617522619979127, "children": { "_process_rank_one_or_two_observation": { "total": 77.25830264098886, "count": 508040, "is_parallel": true, "self": 77.25830264098886 } } } } } } } } } } }, "trainer_advance": { "total": 676.1179315669779, "count": 63506, "self": 2.881195530977493, "children": { "process_trajectory": { "total": 132.5928473019967, "count": 63506, "self": 132.38681599099618, "children": { "RLTrainer._checkpoint": { "total": 0.20603131100051542, "count": 2, "self": 0.20603131100051542 } } }, "_update_policy": { "total": 540.6438887340037, "count": 452, "self": 326.21513820401924, "children": { "TorchPPOOptimizer.update": { "total": 214.42875052998443, "count": 22749, "self": 214.42875052998443 } } } } } } }, "trainer_threads": { "total": 1.1980000635958277e-06, "count": 1, "self": 1.1980000635958277e-06 }, "TrainerController._save_models": { "total": 0.11230866899995817, "count": 1, "self": 0.0017506489998595498, "children": { "RLTrainer._checkpoint": { "total": 0.11055802000009862, "count": 1, "self": 0.11055802000009862 } } } } } } }