{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5226655602455139, "min": 0.5226655602455139, "max": 1.495460033416748, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15596.33984375, "min": 15596.33984375, "max": 45366.27734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4031621515750885, "min": -0.087301105260849, "max": 0.4031621515750885, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.45062255859375, "min": -21.039566040039062, "max": 108.45062255859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03888430818915367, "min": -0.013721240684390068, "max": 0.440623939037323, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.459878921508789, "min": -3.5812437534332275, "max": 104.42787170410156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06518822666701107, "min": 0.06400905932592135, "max": 0.07545935446017188, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.912635173338155, "min": 0.5047046405133784, "max": 1.0341924493550323, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01575132667910241, "min": 0.0004330962430524843, "max": 0.01575132667910241, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22051857350743373, "min": 0.005630251159682295, "max": 0.22051857350743373, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.534254631471427e-06, "min": 7.534254631471427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010547956484059998, "min": 0.00010547956484059998, "max": 0.0036089247970251, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251138571428572, "min": 0.10251138571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351594, "min": 1.3886848, "max": 2.569162500000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002608874328571428, "min": 0.0002608874328571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00365242406, "min": 0.00365242406, "max": 0.12030719251, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013385926373302937, "min": 0.013385926373302937, "max": 0.5761869549751282, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18740296363830566, "min": 0.18740296363830566, "max": 4.033308506011963, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 434.2857142857143, "min": 434.2857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30400.0, "min": 15984.0, "max": 33845.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4799799785017966, "min": -1.0000000521540642, "max": 1.4799799785017966, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.59859849512577, "min": -30.74380173534155, "max": 103.59859849512577, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4799799785017966, "min": -1.0000000521540642, "max": 1.4799799785017966, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.59859849512577, "min": -30.74380173534155, "max": 103.59859849512577, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.061112541359034364, "min": 0.061112541359034364, "max": 11.821637786924839, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.277877895132406, "min": 4.277877895132406, "max": 189.14620459079742, "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": "1678730041", "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": "1678732126" }, "total": 2084.27358121, "count": 1, "self": 0.47456795499965665, "children": { "run_training.setup": { "total": 0.10628328000007059, "count": 1, "self": 0.10628328000007059 }, "TrainerController.start_learning": { "total": 2083.6927299750005, "count": 1, "self": 1.5025811670475377, "children": { "TrainerController._reset_env": { "total": 8.315415677999908, "count": 1, "self": 8.315415677999908 }, "TrainerController.advance": { "total": 2073.780391438953, "count": 63492, "self": 1.535912382988954, "children": { "env_step": { "total": 1440.9111832489484, "count": 63492, "self": 1327.0256248498995, "children": { "SubprocessEnvManager._take_step": { "total": 112.98512790304994, "count": 63492, "self": 4.741314884040776, "children": { "TorchPolicy.evaluate": { "total": 108.24381301900917, "count": 62568, "self": 108.24381301900917 } } }, "workers": { "total": 0.9004304959989895, "count": 63492, "self": 0.0, "children": { "worker_root": { "total": 2079.0188786290378, "count": 63492, "is_parallel": true, "self": 870.1520676210703, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002583831000038117, "count": 1, "is_parallel": true, "self": 0.0006897480000134237, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018940830000246933, "count": 8, "is_parallel": true, "self": 0.0018940830000246933 } } }, "UnityEnvironment.step": { "total": 0.045769880000079866, "count": 1, "is_parallel": true, "self": 0.0005115349999869068, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004476740000427526, "count": 1, "is_parallel": true, "self": 0.0004476740000427526 }, "communicator.exchange": { "total": 0.04323337400001037, "count": 1, "is_parallel": true, "self": 0.04323337400001037 }, "steps_from_proto": { "total": 0.0015772970000398345, "count": 1, "is_parallel": true, "self": 0.00037516400016102125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012021329998788133, "count": 8, "is_parallel": true, "self": 0.0012021329998788133 } } } } } } }, "UnityEnvironment.step": { "total": 1208.8668110079675, "count": 63491, "is_parallel": true, "self": 31.070592564035678, "children": { "UnityEnvironment._generate_step_input": { "total": 22.684635536995074, "count": 63491, "is_parallel": true, "self": 22.684635536995074 }, "communicator.exchange": { "total": 1063.004125210943, "count": 63491, "is_parallel": true, "self": 1063.004125210943 }, "steps_from_proto": { "total": 92.10745769599384, "count": 63491, "is_parallel": true, "self": 20.054575236810706, "children": { "_process_rank_one_or_two_observation": { "total": 72.05288245918314, "count": 507928, "is_parallel": true, "self": 72.05288245918314 } } } } } } } } } } }, "trainer_advance": { "total": 631.3332958070155, "count": 63492, "self": 2.871817751034996, "children": { "process_trajectory": { "total": 117.24316144597856, "count": 63492, "self": 116.9126582959791, "children": { "RLTrainer._checkpoint": { "total": 0.3305031499994584, "count": 2, "self": 0.3305031499994584 } } }, "_update_policy": { "total": 511.2183166100019, "count": 452, "self": 323.5419686030625, "children": { "TorchPPOOptimizer.update": { "total": 187.6763480069394, "count": 22773, "self": 187.6763480069394 } } } } } } }, "trainer_threads": { "total": 8.910001270123757e-07, "count": 1, "self": 8.910001270123757e-07 }, "TrainerController._save_models": { "total": 0.09434080000028189, "count": 1, "self": 0.001544221000131074, "children": { "RLTrainer._checkpoint": { "total": 0.09279657900015081, "count": 1, "self": 0.09279657900015081 } } } } } } }