{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31433817744255066, "min": 0.3107055127620697, "max": 1.4778294563293457, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9389.91015625, "min": 9236.6533203125, "max": 44831.43359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4244847297668457, "min": -0.1057375818490982, "max": 0.45465967059135437, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.06396484375, "min": -25.482757568359375, "max": 121.84879302978516, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008258827961981297, "min": -0.008258827961981297, "max": 0.4409588873386383, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.180330514907837, "min": -2.180330514907837, "max": 104.50725555419922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06735845976441489, "min": 0.06426652848947967, "max": 0.07231086811037077, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9430184367018085, "min": 0.4805312172630829, "max": 1.0846630216555615, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012514834956209978, "min": 0.0001498434430330268, "max": 0.01422720983845509, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1752076893869397, "min": 0.0019479647594293486, "max": 0.19918093773837126, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.573490332678569e-06, "min": 7.573490332678569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010602886465749996, "min": 0.00010602886465749996, "max": 0.0032600108133297996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252446428571428, "min": 0.10252446428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353425, "min": 1.3886848, "max": 2.4003979999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002621939821428571, "min": 0.0002621939821428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036707157499999993, "min": 0.0036707157499999993, "max": 0.10868835298000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008687932044267654, "min": 0.008687932044267654, "max": 0.4169345796108246, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12163104861974716, "min": 0.12163104861974716, "max": 2.9185421466827393, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 457.203125, "min": 413.93150684931504, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29261.0, "min": 15984.0, "max": 32691.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.323962468188256, "min": -1.0000000521540642, "max": 1.4216383372063506, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.73359796404839, "min": -30.996801614761353, "max": 103.7795986160636, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.323962468188256, "min": -1.0000000521540642, "max": 1.4216383372063506, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.73359796404839, "min": -30.996801614761353, "max": 103.7795986160636, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.041725836785417414, "min": 0.041725836785417414, "max": 8.767399423755705, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6704535542667145, "min": 2.6704535542667145, "max": 140.27839078009129, "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": "1674775458", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674777336" }, "total": 1877.8551097109998, "count": 1, "self": 0.44019972799969764, "children": { "run_training.setup": { "total": 0.10507932300015455, "count": 1, "self": 0.10507932300015455 }, "TrainerController.start_learning": { "total": 1877.30983066, "count": 1, "self": 1.1553366238999843, "children": { "TrainerController._reset_env": { "total": 5.930306977999862, "count": 1, "self": 5.930306977999862 }, "TrainerController.advance": { "total": 1870.1371537781001, "count": 63524, "self": 1.1421977990898995, "children": { "env_step": { "total": 1234.564970867962, "count": 63524, "self": 1136.955734141935, "children": { "SubprocessEnvManager._take_step": { "total": 96.92138252896939, "count": 63524, "self": 3.9689190299855, "children": { "TorchPolicy.evaluate": { "total": 92.95246349898389, "count": 62539, "self": 31.22020294389904, "children": { "TorchPolicy.sample_actions": { "total": 61.73226055508485, "count": 62539, "self": 61.73226055508485 } } } } }, "workers": { "total": 0.6878541970577317, "count": 63524, "self": 0.0, "children": { "worker_root": { "total": 1874.4633532230328, "count": 63524, "is_parallel": true, "self": 828.1868648270802, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020233929999449174, "count": 1, "is_parallel": true, "self": 0.0007120590003069083, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013113339996380091, "count": 8, "is_parallel": true, "self": 0.0013113339996380091 } } }, "UnityEnvironment.step": { "total": 0.04538371200032998, "count": 1, "is_parallel": true, "self": 0.0004917390006085043, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044048499967175303, "count": 1, "is_parallel": true, "self": 0.00044048499967175303 }, "communicator.exchange": { "total": 0.04288847399993756, "count": 1, "is_parallel": true, "self": 0.04288847399993756 }, "steps_from_proto": { "total": 0.0015630140001121617, "count": 1, "is_parallel": true, "self": 0.0004352210003162327, "children": { "_process_rank_one_or_two_observation": { "total": 0.001127792999795929, "count": 8, "is_parallel": true, "self": 0.001127792999795929 } } } } } } }, "UnityEnvironment.step": { "total": 1046.2764883959526, "count": 63523, "is_parallel": true, "self": 26.667877326900907, "children": { "UnityEnvironment._generate_step_input": { "total": 21.01074237999319, "count": 63523, "is_parallel": true, "self": 21.01074237999319 }, "communicator.exchange": { "total": 912.6689811420233, "count": 63523, "is_parallel": true, "self": 912.6689811420233 }, "steps_from_proto": { "total": 85.92888754703517, "count": 63523, "is_parallel": true, "self": 19.855138650166737, "children": { "_process_rank_one_or_two_observation": { "total": 66.07374889686844, "count": 508184, "is_parallel": true, "self": 66.07374889686844 } } } } } } } } } } }, "trainer_advance": { "total": 634.4299851110482, "count": 63524, "self": 2.0931676060026803, "children": { "process_trajectory": { "total": 137.73372421304384, "count": 63524, "self": 137.53056724404405, "children": { "RLTrainer._checkpoint": { "total": 0.2031569689997923, "count": 2, "self": 0.2031569689997923 } } }, "_update_policy": { "total": 494.60309329200163, "count": 446, "self": 185.92460715299694, "children": { "TorchPPOOptimizer.update": { "total": 308.6784861390047, "count": 22851, "self": 308.6784861390047 } } } } } } }, "trainer_threads": { "total": 9.830000635702163e-07, "count": 1, "self": 9.830000635702163e-07 }, "TrainerController._save_models": { "total": 0.08703229699995063, "count": 1, "self": 0.0019373919999452482, "children": { "RLTrainer._checkpoint": { "total": 0.08509490500000538, "count": 1, "self": 0.08509490500000538 } } } } } } }