{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34801602363586426, "min": 0.34801602363586426, "max": 1.4562019109725952, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10412.6396484375, "min": 10412.6396484375, "max": 44175.33984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6144884824752808, "min": -0.10223714262247086, "max": 0.6887772083282471, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 170.21331787109375, "min": -24.536914825439453, "max": 201.8117218017578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010971937328577042, "min": 0.0001569524611113593, "max": 0.540977954864502, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.039226531982422, "min": 0.04316192865371704, "max": 128.21177673339844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0725075410455935, "min": 0.06660226467769872, "max": 0.07447525693426918, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0151055746383089, "min": 0.5213267985398843, "max": 1.0489560605341535, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01617024436932845, "min": 0.0017720839496364698, "max": 0.016416300733159434, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2263834211705983, "min": 0.015948755546728227, "max": 0.22982821026423206, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.604540322328572e-06, "min": 7.604540322328572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010646356451260001, "min": 0.00010646356451260001, "max": 0.0037600897466368, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253481428571429, "min": 0.10253481428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354874, "min": 1.3886848, "max": 2.6533632000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026322794714285725, "min": 0.00026322794714285725, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003685191260000001, "min": 0.003685191260000001, "max": 0.12535098368000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00975178275257349, "min": 0.00917449127882719, "max": 0.40368324518203735, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.136524960398674, "min": 0.1284428834915161, "max": 2.8257827758789062, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 310.08247422680415, "min": 269.52252252252254, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30078.0, "min": 15984.0, "max": 32856.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6899175049410653, "min": -1.0000000521540642, "max": 1.6944252035773553, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.92199797928333, "min": -30.63660169392824, "max": 188.08119759708643, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6899175049410653, "min": -1.0000000521540642, "max": 1.6944252035773553, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.92199797928333, "min": -30.63660169392824, "max": 188.08119759708643, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030962497451985926, "min": 0.02659012440235201, "max": 7.840575894340873, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.003362252842635, "min": 2.897797493133112, "max": 125.44921430945396, "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": "1686697313", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686699702" }, "total": 2388.469017284, "count": 1, "self": 0.7303379659997518, "children": { "run_training.setup": { "total": 0.03687182200019379, "count": 1, "self": 0.03687182200019379 }, "TrainerController.start_learning": { "total": 2387.701807496, "count": 1, "self": 1.476610344004257, "children": { "TrainerController._reset_env": { "total": 4.054023206000011, "count": 1, "self": 4.054023206000011 }, "TrainerController.advance": { "total": 2382.0197317729967, "count": 64325, "self": 1.508990389990231, "children": { "env_step": { "total": 1717.9566113660444, "count": 64325, "self": 1600.3587634590142, "children": { "SubprocessEnvManager._take_step": { "total": 116.75734893800131, "count": 64325, "self": 4.976515230032874, "children": { "TorchPolicy.evaluate": { "total": 111.78083370796844, "count": 62567, "self": 111.78083370796844 } } }, "workers": { "total": 0.8404989690288858, "count": 64325, "self": 0.0, "children": { "worker_root": { "total": 2381.9515975980094, "count": 64325, "is_parallel": true, "self": 901.7574260400315, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00174986899992291, "count": 1, "is_parallel": true, "self": 0.0005453109995414707, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012045580003814393, "count": 8, "is_parallel": true, "self": 0.0012045580003814393 } } }, "UnityEnvironment.step": { "total": 0.04724902400016617, "count": 1, "is_parallel": true, "self": 0.0006246810000902769, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047481399997195695, "count": 1, "is_parallel": true, "self": 0.00047481399997195695 }, "communicator.exchange": { "total": 0.044084359999942535, "count": 1, "is_parallel": true, "self": 0.044084359999942535 }, "steps_from_proto": { "total": 0.0020651690001614043, "count": 1, "is_parallel": true, "self": 0.0004205590000765369, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016446100000848674, "count": 8, "is_parallel": true, "self": 0.0016446100000848674 } } } } } } }, "UnityEnvironment.step": { "total": 1480.1941715579778, "count": 64324, "is_parallel": true, "self": 34.6187939669619, "children": { "UnityEnvironment._generate_step_input": { "total": 23.14167623200433, "count": 64324, "is_parallel": true, "self": 23.14167623200433 }, "communicator.exchange": { "total": 1316.945222044939, "count": 64324, "is_parallel": true, "self": 1316.945222044939 }, "steps_from_proto": { "total": 105.48847931407249, "count": 64324, "is_parallel": true, "self": 21.079352646211873, "children": { "_process_rank_one_or_two_observation": { "total": 84.40912666786062, "count": 514592, "is_parallel": true, "self": 84.40912666786062 } } } } } } } } } } }, "trainer_advance": { "total": 662.5541300169623, "count": 64325, "self": 2.8914766769421476, "children": { "process_trajectory": { "total": 114.26637851402143, "count": 64325, "self": 113.99982044702142, "children": { "RLTrainer._checkpoint": { "total": 0.2665580670000054, "count": 2, "self": 0.2665580670000054 } } }, "_update_policy": { "total": 545.3962748259987, "count": 459, "self": 347.8542660400053, "children": { "TorchPPOOptimizer.update": { "total": 197.5420087859934, "count": 22791, "self": 197.5420087859934 } } } } } } }, "trainer_threads": { "total": 1.3679996300197672e-06, "count": 1, "self": 1.3679996300197672e-06 }, "TrainerController._save_models": { "total": 0.15144080499976553, "count": 1, "self": 0.0017683859996395768, "children": { "RLTrainer._checkpoint": { "total": 0.14967241900012596, "count": 1, "self": 0.14967241900012596 } } } } } } }