{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4007338285446167, "min": 0.4007338285446167, "max": 1.3617796897888184, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12054.0732421875, "min": 12054.0732421875, "max": 41310.94921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5167332887649536, "min": -0.1756802648305893, "max": 0.5668001770973206, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.5849151611328, "min": -41.63622283935547, "max": 155.87005615234375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027599532157182693, "min": -0.01235404796898365, "max": 0.40753263235092163, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.562271595001221, "min": -3.039095878601074, "max": 96.58523559570312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07125376545097249, "min": 0.06503431373951644, "max": 0.07221301006413561, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9975527163136149, "min": 0.504053860147592, "max": 1.0604980054577386, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016308116192660583, "min": 0.0004030147861963387, "max": 0.01719744702166368, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22831362669724817, "min": 0.004433162648159726, "max": 0.24076425830329148, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.595776039535712e-06, "min": 7.595776039535712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010634086455349997, "min": 0.00010634086455349997, "max": 0.0032583425138859, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253189285714288, "min": 0.10253189285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354465000000003, "min": 1.3886848, "max": 2.386114100000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026293609642857136, "min": 0.00026293609642857136, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003681105349999999, "min": 0.003681105349999999, "max": 0.10863279859000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010332442820072174, "min": 0.010332442820072174, "max": 0.408700555562973, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14465419948101044, "min": 0.14465419948101044, "max": 2.8609039783477783, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 336.17857142857144, "min": 336.17857142857144, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28239.0, "min": 15984.0, "max": 34501.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5903686556112335, "min": -1.0000000521540642, "max": 1.6232278924002204, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.00059841573238, "min": -31.998801663517952, "max": 144.05919805914164, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5903686556112335, "min": -1.0000000521540642, "max": 1.6232278924002204, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.00059841573238, "min": -31.998801663517952, "max": 144.05919805914164, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03684224781765412, "min": 0.03684224781765412, "max": 8.432015168480575, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0579065688652918, "min": 3.0579065688652918, "max": 134.9122426956892, "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": "1769408598", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1769409735" }, "total": 1136.744697859991, "count": 1, "self": 0.1676571380085079, "children": { "run_training.setup": { "total": 0.01158668399148155, "count": 1, "self": 0.01158668399148155 }, "TrainerController.start_learning": { "total": 1136.565454037991, "count": 1, "self": 0.6505314587702742, "children": { "TrainerController._reset_env": { "total": 1.1264060269895708, "count": 1, "self": 1.1264060269895708 }, "TrainerController.advance": { "total": 1134.7384799922293, "count": 63554, "self": 0.5691899509256473, "children": { "env_step": { "total": 731.2098398360686, "count": 63554, "self": 587.9705909335898, "children": { "SubprocessEnvManager._take_step": { "total": 142.8158826885192, "count": 63554, "self": 2.1951552999962587, "children": { "TorchPolicy.evaluate": { "total": 140.62072738852294, "count": 62552, "self": 140.62072738852294 } } }, "workers": { "total": 0.42336621395952534, "count": 63554, "self": 0.0, "children": { "worker_root": { "total": 1134.8624866543687, "count": 63554, "is_parallel": true, "self": 590.0661611034739, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001056043998687528, "count": 1, "is_parallel": true, "self": 0.0004032040305901319, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006528399680973962, "count": 8, "is_parallel": true, "self": 0.0006528399680973962 } } }, "UnityEnvironment.step": { "total": 0.017967605992453173, "count": 1, "is_parallel": true, "self": 0.0001353109983028844, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00012591300765052438, "count": 1, "is_parallel": true, "self": 0.00012591300765052438 }, "communicator.exchange": { "total": 0.017336477991193533, "count": 1, "is_parallel": true, "self": 0.017336477991193533 }, "steps_from_proto": { "total": 0.0003699039953062311, "count": 1, "is_parallel": true, "self": 8.928899478632957e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0002806150005199015, "count": 8, "is_parallel": true, "self": 0.0002806150005199015 } } } } } } }, "UnityEnvironment.step": { "total": 544.7963255508948, "count": 63553, "is_parallel": true, "self": 8.297103372126003, "children": { "UnityEnvironment._generate_step_input": { "total": 6.096956301786122, "count": 63553, "is_parallel": true, "self": 6.096956301786122 }, "communicator.exchange": { "total": 508.464210834456, "count": 63553, "is_parallel": true, "self": 508.464210834456 }, "steps_from_proto": { "total": 21.938055042526685, "count": 63553, "is_parallel": true, "self": 4.911037722267793, "children": { "_process_rank_one_or_two_observation": { "total": 17.027017320258892, "count": 508424, "is_parallel": true, "self": 17.027017320258892 } } } } } } } } } } }, "trainer_advance": { "total": 402.95945020523504, "count": 63554, "self": 1.0695041164581198, "children": { "process_trajectory": { "total": 65.48276216773957, "count": 63554, "self": 65.36784009373514, "children": { "RLTrainer._checkpoint": { "total": 0.11492207400442567, "count": 2, "self": 0.11492207400442567 } } }, "_update_policy": { "total": 336.40718392103736, "count": 443, "self": 143.994703530494, "children": { "TorchPPOOptimizer.update": { "total": 192.41248039054335, "count": 22872, "self": 192.41248039054335 } } } } } } }, "trainer_threads": { "total": 4.2900501284748316e-07, "count": 1, "self": 4.2900501284748316e-07 }, "TrainerController._save_models": { "total": 0.05003613099688664, "count": 1, "self": 0.0009081850002985448, "children": { "RLTrainer._checkpoint": { "total": 0.049127945996588096, "count": 1, "self": 0.049127945996588096 } } } } } } }