{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3623613119125366, "min": 0.3623613119125366, "max": 1.4597163200378418, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10841.8505859375, "min": 10841.8505859375, "max": 44281.953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7121767997741699, "min": -0.07842103391885757, "max": 0.7330880761146545, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 207.95562744140625, "min": -18.821048736572266, "max": 214.8376922607422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022392867133021355, "min": 0.017170555889606476, "max": 0.457565575838089, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.538717269897461, "min": 4.687561988830566, "max": 109.81573486328125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06928242601117947, "min": 0.06547740072225376, "max": 0.07207416939837415, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.039236390167692, "min": 0.4827421773810491, "max": 1.056197498740706, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015814841035494787, "min": 0.001528092591167077, "max": 0.017331028425423962, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2372226155324218, "min": 0.012266789816608094, "max": 0.24263439795593547, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.510717496460002e-06, "min": 7.510717496460002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011266076244690003, "min": 0.00011266076244690003, "max": 0.0036334594888468995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250354000000002, "min": 0.10250354000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375531000000002, "min": 1.3691136000000002, "max": 2.6175173000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026010364600000005, "min": 0.00026010364600000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003901554690000001, "min": 0.003901554690000001, "max": 0.12113419469000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014273879118263721, "min": 0.014273879118263721, "max": 0.6075441241264343, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2141081839799881, "min": 0.20748208463191986, "max": 4.252809047698975, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 272.10280373831773, "min": 249.5655737704918, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29115.0, "min": 15984.0, "max": 33352.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.709196248970856, "min": -1.0000000521540642, "max": 1.7516991708094511, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 182.8839986398816, "min": -32.000001668930054, "max": 215.4589980095625, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.709196248970856, "min": -1.0000000521540642, "max": 1.7516991708094511, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 182.8839986398816, "min": -32.000001668930054, "max": 215.4589980095625, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040126602303576175, "min": 0.03802241957890782, "max": 12.24424483627081, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.293546446482651, "min": 4.293546446482651, "max": 195.90791738033295, "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": "1748956599", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748958937" }, "total": 2337.8721931289997, "count": 1, "self": 0.47583602499935296, "children": { "run_training.setup": { "total": 0.02806961499982208, "count": 1, "self": 0.02806961499982208 }, "TrainerController.start_learning": { "total": 2337.3682874890005, "count": 1, "self": 1.3382924150118924, "children": { "TrainerController._reset_env": { "total": 2.625964748000115, "count": 1, "self": 2.625964748000115 }, "TrainerController.advance": { "total": 2333.324025422988, "count": 64446, "self": 1.4095005940198462, "children": { "env_step": { "total": 1662.5593968820185, "count": 64446, "self": 1515.2147191770405, "children": { "SubprocessEnvManager._take_step": { "total": 146.5989373608113, "count": 64446, "self": 4.5510353537911215, "children": { "TorchPolicy.evaluate": { "total": 142.04790200702018, "count": 62562, "self": 142.04790200702018 } } }, "workers": { "total": 0.7457403441667338, "count": 64446, "self": 0.0, "children": { "worker_root": { "total": 2332.5359417021036, "count": 64446, "is_parallel": true, "self": 927.9723316081286, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020017169999846374, "count": 1, "is_parallel": true, "self": 0.0006582520004485559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013434649995360815, "count": 8, "is_parallel": true, "self": 0.0013434649995360815 } } }, "UnityEnvironment.step": { "total": 0.047814576999826386, "count": 1, "is_parallel": true, "self": 0.0005682400001205679, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004454729996723472, "count": 1, "is_parallel": true, "self": 0.0004454729996723472 }, "communicator.exchange": { "total": 0.04523406999987856, "count": 1, "is_parallel": true, "self": 0.04523406999987856 }, "steps_from_proto": { "total": 0.001566794000154914, "count": 1, "is_parallel": true, "self": 0.0003541410005709622, "children": { "_process_rank_one_or_two_observation": { "total": 0.001212652999583952, "count": 8, "is_parallel": true, "self": 0.001212652999583952 } } } } } } }, "UnityEnvironment.step": { "total": 1404.563610093975, "count": 64445, "is_parallel": true, "self": 31.3379355910065, "children": { "UnityEnvironment._generate_step_input": { "total": 22.65854317603589, "count": 64445, "is_parallel": true, "self": 22.65854317603589 }, "communicator.exchange": { "total": 1257.5746788039805, "count": 64445, "is_parallel": true, "self": 1257.5746788039805 }, "steps_from_proto": { "total": 92.99245252295214, "count": 64445, "is_parallel": true, "self": 18.465762725118566, "children": { "_process_rank_one_or_two_observation": { "total": 74.52668979783357, "count": 515560, "is_parallel": true, "self": 74.52668979783357 } } } } } } } } } } }, "trainer_advance": { "total": 669.3551279469498, "count": 64446, "self": 2.547122582981501, "children": { "process_trajectory": { "total": 128.92563509397587, "count": 64446, "self": 128.68909866197646, "children": { "RLTrainer._checkpoint": { "total": 0.23653643199941143, "count": 2, "self": 0.23653643199941143 } } }, "_update_policy": { "total": 537.8823702699924, "count": 451, "self": 298.68874422200724, "children": { "TorchPPOOptimizer.update": { "total": 239.19362604798516, "count": 22797, "self": 239.19362604798516 } } } } } } }, "trainer_threads": { "total": 9.10000380827114e-07, "count": 1, "self": 9.10000380827114e-07 }, "TrainerController._save_models": { "total": 0.08000399299999117, "count": 1, "self": 0.0011264970007687225, "children": { "RLTrainer._checkpoint": { "total": 0.07887749599922245, "count": 1, "self": 0.07887749599922245 } } } } } } }