{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6287679076194763, "min": 0.5319587588310242, "max": 1.4029192924499512, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18963.640625, "min": 15831.0927734375, "max": 42558.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.14135169982910156, "min": -0.11004143953323364, "max": 0.2635327875614166, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 35.9033317565918, "min": -26.519987106323242, "max": 69.04559326171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.3652493953704834, "min": -0.6096718907356262, "max": 0.44557034969329834, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -92.77334594726562, "min": -155.46633911132812, "max": 105.60017395019531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06646148416600764, "min": 0.06499414287558805, "max": 0.0742191102739885, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9304607783241069, "min": 0.488508802903689, "max": 1.039067543835839, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.025967431604155083, "min": 0.001095567189611388, "max": 0.051618459581818786, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3635440424581712, "min": 0.01533794065455943, "max": 0.722658434145463, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.682604582021425e-06, "min": 7.682604582021425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010755646414829995, "min": 0.00010755646414829995, "max": 0.0036322933892355995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256083571428572, "min": 0.10256083571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358517, "min": 1.3886848, "max": 2.6107644000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002658274878571428, "min": 0.0002658274878571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037215848299999997, "min": 0.0037215848299999997, "max": 0.12109536355999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013697878457605839, "min": 0.013697878457605839, "max": 0.5452428460121155, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1917703002691269, "min": 0.1917703002691269, "max": 3.816699743270874, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 702.6, "min": 565.3636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31617.0, "min": 15984.0, "max": 33088.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5692954158241098, "min": -1.0000000521540642, "max": 1.080951815953961, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 25.048998296260834, "min": -28.346001639962196, "max": 58.3713980615139, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5692954158241098, "min": -1.0000000521540642, "max": 1.080951815953961, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 25.048998296260834, "min": -28.346001639962196, "max": 58.3713980615139, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09928790991596709, "min": 0.08714899166741154, "max": 11.177472366020083, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.368668036302552, "min": 4.0597703823732445, "max": 178.83955785632133, "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": "1685966511", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 --force", "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": "1685968660" }, "total": 2149.336377734, "count": 1, "self": 0.4798384519999672, "children": { "run_training.setup": { "total": 0.037114259000077254, "count": 1, "self": 0.037114259000077254 }, "TrainerController.start_learning": { "total": 2148.819425023, "count": 1, "self": 1.643690671998229, "children": { "TrainerController._reset_env": { "total": 4.964506325000002, "count": 1, "self": 4.964506325000002 }, "TrainerController.advance": { "total": 2142.112218533001, "count": 63448, "self": 1.5758214751022024, "children": { "env_step": { "total": 1492.023451818951, "count": 63448, "self": 1371.9111056189604, "children": { "SubprocessEnvManager._take_step": { "total": 119.1667396389496, "count": 63448, "self": 5.19649645389984, "children": { "TorchPolicy.evaluate": { "total": 113.97024318504975, "count": 62567, "self": 113.97024318504975 } } }, "workers": { "total": 0.9456065610410178, "count": 63448, "self": 0.0, "children": { "worker_root": { "total": 2143.3078322000556, "count": 63448, "is_parallel": true, "self": 894.5533605340302, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025185999999166597, "count": 1, "is_parallel": true, "self": 0.0007142949999661141, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018043049999505456, "count": 8, "is_parallel": true, "self": 0.0018043049999505456 } } }, "UnityEnvironment.step": { "total": 0.04737434900005155, "count": 1, "is_parallel": true, "self": 0.0005682320000914842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005273859999306296, "count": 1, "is_parallel": true, "self": 0.0005273859999306296 }, "communicator.exchange": { "total": 0.044436594999979206, "count": 1, "is_parallel": true, "self": 0.044436594999979206 }, "steps_from_proto": { "total": 0.0018421360000502318, "count": 1, "is_parallel": true, "self": 0.00037471400014510436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014674219999051274, "count": 8, "is_parallel": true, "self": 0.0014674219999051274 } } } } } } }, "UnityEnvironment.step": { "total": 1248.7544716660254, "count": 63447, "is_parallel": true, "self": 32.852734957933535, "children": { "UnityEnvironment._generate_step_input": { "total": 25.05891852507625, "count": 63447, "is_parallel": true, "self": 25.05891852507625 }, "communicator.exchange": { "total": 1083.6360469910442, "count": 63447, "is_parallel": true, "self": 1083.6360469910442 }, "steps_from_proto": { "total": 107.20677119197148, "count": 63447, "is_parallel": true, "self": 22.720437267046805, "children": { "_process_rank_one_or_two_observation": { "total": 84.48633392492468, "count": 507576, "is_parallel": true, "self": 84.48633392492468 } } } } } } } } } } }, "trainer_advance": { "total": 648.5129452389479, "count": 63448, "self": 2.986872120966268, "children": { "process_trajectory": { "total": 112.51092930797961, "count": 63448, "self": 112.23462491697967, "children": { "RLTrainer._checkpoint": { "total": 0.27630439099993964, "count": 2, "self": 0.27630439099993964 } } }, "_update_policy": { "total": 533.015143810002, "count": 454, "self": 347.0429142979734, "children": { "TorchPPOOptimizer.update": { "total": 185.97222951202855, "count": 22788, "self": 185.97222951202855 } } } } } } }, "trainer_threads": { "total": 1.2530003914434928e-06, "count": 1, "self": 1.2530003914434928e-06 }, "TrainerController._save_models": { "total": 0.09900824000033026, "count": 1, "self": 0.0019622220002020185, "children": { "RLTrainer._checkpoint": { "total": 0.09704601800012824, "count": 1, "self": 0.09704601800012824 } } } } } } }