{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4059933125972748, "min": 0.39715439081192017, "max": 1.391348123550415, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12205.783203125, "min": 11901.9228515625, "max": 42207.9375, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29896.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29896.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46790915727615356, "min": -0.1095510721206665, "max": 0.4824177026748657, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.73919677734375, "min": -26.40180778503418, "max": 132.6648712158203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.052653852850198746, "min": -0.06417358666658401, "max": 0.36108410358428955, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -14.374502182006836, "min": -16.492610931396484, "max": 85.57693481445312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07295300758033547, "min": 0.06457576945716803, "max": 0.07571827622368271, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0213421061246966, "min": 0.6814644860131444, "max": 1.0510492202204964, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01587568756804103, "min": 0.00016397854359953543, "max": 0.01587568756804103, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22225962595257442, "min": 0.0021317210667939606, "max": 0.22225962595257442, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.366597544500002e-06, "min": 7.366597544500002e-06, "max": 0.0002948651017116333, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010313236562300003, "min": 0.00010313236562300003, "max": 0.0033821882726039997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024555, "min": 0.1024555, "max": 0.1982883666666667, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434377, "min": 1.434377, "max": 2.527396, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002553044500000001, "min": 0.0002553044500000001, "max": 0.009829007829999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003574262300000001, "min": 0.003574262300000001, "max": 0.11276686039999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016512218862771988, "min": 0.016512218862771988, "max": 0.4444085359573364, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23117107152938843, "min": 0.23117107152938843, "max": 3.9996767044067383, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 396.82894736842104, "min": 382.13157894736844, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30159.0, "min": 16439.0, "max": 32427.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5242026057094336, "min": -0.9999125516042113, "max": 1.5242026057094336, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.83939803391695, "min": -31.997201651334763, "max": 115.83939803391695, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5242026057094336, "min": -0.9999125516042113, "max": 1.5242026057094336, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.83939803391695, "min": -31.997201651334763, "max": 115.83939803391695, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06795989735186786, "min": 0.06590360357720208, "max": 9.615516344414038, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.1649521987419575, "min": 5.008673871867359, "max": 163.46377785503864, "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": "1680692242", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680694300" }, "total": 2058.175234011, "count": 1, "self": 0.4242503720001878, "children": { "run_training.setup": { "total": 0.10575246900043567, "count": 1, "self": 0.10575246900043567 }, "TrainerController.start_learning": { "total": 2057.6452311699995, "count": 1, "self": 1.393002608034294, "children": { "TrainerController._reset_env": { "total": 4.364087276999726, "count": 1, "self": 4.364087276999726 }, "TrainerController.advance": { "total": 2051.796258510965, "count": 63608, "self": 1.397841679100111, "children": { "env_step": { "total": 1450.4963841819126, "count": 63608, "self": 1345.9276786417827, "children": { "SubprocessEnvManager._take_step": { "total": 103.76707985005169, "count": 63608, "self": 4.65658583204231, "children": { "TorchPolicy.evaluate": { "total": 99.11049401800938, "count": 62559, "self": 99.11049401800938 } } }, "workers": { "total": 0.8016256900782537, "count": 63608, "self": 0.0, "children": { "worker_root": { "total": 2052.885664612976, "count": 63608, "is_parallel": true, "self": 813.1550638510248, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018020560000877595, "count": 1, "is_parallel": true, "self": 0.0005594770004790917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012425789996086678, "count": 8, "is_parallel": true, "self": 0.0012425789996086678 } } }, "UnityEnvironment.step": { "total": 0.11026811200008524, "count": 1, "is_parallel": true, "self": 0.0005845370001225092, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042601399991326616, "count": 1, "is_parallel": true, "self": 0.00042601399991326616 }, "communicator.exchange": { "total": 0.09954681099998197, "count": 1, "is_parallel": true, "self": 0.09954681099998197 }, "steps_from_proto": { "total": 0.009710750000067492, "count": 1, "is_parallel": true, "self": 0.008496582000589115, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012141679994783772, "count": 8, "is_parallel": true, "self": 0.0012141679994783772 } } } } } } }, "UnityEnvironment.step": { "total": 1239.7306007619513, "count": 63607, "is_parallel": true, "self": 31.617140868037495, "children": { "UnityEnvironment._generate_step_input": { "total": 22.3351962899701, "count": 63607, "is_parallel": true, "self": 22.3351962899701 }, "communicator.exchange": { "total": 1095.3404195850026, "count": 63607, "is_parallel": true, "self": 1095.3404195850026 }, "steps_from_proto": { "total": 90.43784401894118, "count": 63607, "is_parallel": true, "self": 19.14610923491864, "children": { "_process_rank_one_or_two_observation": { "total": 71.29173478402254, "count": 508856, "is_parallel": true, "self": 71.29173478402254 } } } } } } } } } } }, "trainer_advance": { "total": 599.9020326499522, "count": 63608, "self": 2.503271927971582, "children": { "process_trajectory": { "total": 101.13825509498338, "count": 63608, "self": 100.93733062598358, "children": { "RLTrainer._checkpoint": { "total": 0.20092446899980132, "count": 2, "self": 0.20092446899980132 } } }, "_update_policy": { "total": 496.2605056269972, "count": 452, "self": 316.4680698309776, "children": { "TorchPPOOptimizer.update": { "total": 179.79243579601962, "count": 22770, "self": 179.79243579601962 } } } } } } }, "trainer_threads": { "total": 8.770002750679851e-07, "count": 1, "self": 8.770002750679851e-07 }, "TrainerController._save_models": { "total": 0.09188189700034854, "count": 1, "self": 0.0014045910011191154, "children": { "RLTrainer._checkpoint": { "total": 0.09047730599922943, "count": 1, "self": 0.09047730599922943 } } } } } } }