{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16854897141456604, "min": 0.15655803680419922, "max": 1.4489586353302002, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5029.50146484375, "min": 4678.2314453125, "max": 43955.609375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999943.0, "min": 29952.0, "max": 2999943.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999943.0, "min": 29952.0, "max": 2999943.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7716683745384216, "min": -0.09531861543655396, "max": 0.859332799911499, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 229.1855010986328, "min": -23.06710433959961, "max": 258.6591796875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002094599884003401, "min": -0.04100258648395538, "max": 0.1930646002292633, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6220961809158325, "min": -11.562728881835938, "max": 46.33550262451172, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06814502403098491, "min": 0.064247308358539, "max": 0.07385510346458975, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9540303364337888, "min": 0.49947003987664623, "max": 1.1070615875457104, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016075876610037607, "min": 0.0006657301072922576, "max": 0.016281632504182027, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2250622725405265, "min": 0.005297017293846641, "max": 0.23126909665491743, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4132209575309482e-06, "min": 1.4132209575309482e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.9785093405433275e-05, "min": 1.9785093405433275e-05, "max": 0.004011222662925799, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10047104047619049, "min": 0.10047104047619049, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4065945666666668, "min": 1.3897045333333333, "max": 2.812525566666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.705694357142843e-05, "min": 5.705694357142843e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000798797209999998, "min": 0.000798797209999998, "max": 0.13371371258, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005239349324256182, "min": 0.004959680140018463, "max": 0.38137850165367126, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07335089147090912, "min": 0.06943552196025848, "max": 2.669649600982666, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 227.3030303030303, "min": 213.2246376811594, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30004.0, "min": 15984.0, "max": 32851.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7726969490900184, "min": -1.0000000521540642, "max": 1.7726969490900184, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 233.99599727988243, "min": -32.000001668930054, "max": 253.35439769923687, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7726969490900184, "min": -1.0000000521540642, "max": 1.7726969490900184, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 233.99599727988243, "min": -32.000001668930054, "max": 253.35439769923687, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012455228235921822, "min": 0.011395999637287487, "max": 7.789177190512419, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6440901271416806, "min": 1.4106278056424344, "max": 124.6268350481987, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679713008", "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": "1679720341" }, "total": 7333.065990769999, "count": 1, "self": 0.5343724680005835, "children": { "run_training.setup": { "total": 0.16641395299984652, "count": 1, "self": 0.16641395299984652 }, "TrainerController.start_learning": { "total": 7332.365204348999, "count": 1, "self": 4.446575348320948, "children": { "TrainerController._reset_env": { "total": 6.9010865189998185, "count": 1, "self": 6.9010865189998185 }, "TrainerController.advance": { "total": 7320.919810476678, "count": 194908, "self": 4.775974526385653, "children": { "env_step": { "total": 5391.985714539169, "count": 194908, "self": 5044.156113320067, "children": { "SubprocessEnvManager._take_step": { "total": 345.03513432614636, "count": 194908, "self": 15.167031256084101, "children": { "TorchPolicy.evaluate": { "total": 329.86810307006226, "count": 187558, "self": 329.86810307006226 } } }, "workers": { "total": 2.7944668929558247, "count": 194908, "self": 0.0, "children": { "worker_root": { "total": 7315.441871167913, "count": 194908, "is_parallel": true, "self": 2647.6509251549387, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002665375000105996, "count": 1, "is_parallel": true, "self": 0.0007571969999844441, "children": { "_process_rank_one_or_two_observation": { "total": 0.001908178000121552, "count": 8, "is_parallel": true, "self": 0.001908178000121552 } } }, "UnityEnvironment.step": { "total": 0.056474290000096516, "count": 1, "is_parallel": true, "self": 0.0007410599996546807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005081460003566463, "count": 1, "is_parallel": true, "self": 0.0005081460003566463 }, "communicator.exchange": { "total": 0.053243288999965444, "count": 1, "is_parallel": true, "self": 0.053243288999965444 }, "steps_from_proto": { "total": 0.001981795000119746, "count": 1, "is_parallel": true, "self": 0.0005342150006981683, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014475799994215777, "count": 8, "is_parallel": true, "self": 0.0014475799994215777 } } } } } } }, "UnityEnvironment.step": { "total": 4667.790946012974, "count": 194907, "is_parallel": true, "self": 96.74719422709495, "children": { "UnityEnvironment._generate_step_input": { "total": 74.5727067619614, "count": 194907, "is_parallel": true, "self": 74.5727067619614 }, "communicator.exchange": { "total": 4197.70342823799, "count": 194907, "is_parallel": true, "self": 4197.70342823799 }, "steps_from_proto": { "total": 298.7676167859281, "count": 194907, "is_parallel": true, "self": 65.24151669198682, "children": { "_process_rank_one_or_two_observation": { "total": 233.5261000939413, "count": 1559256, "is_parallel": true, "self": 233.5261000939413 } } } } } } } } } } }, "trainer_advance": { "total": 1924.1581214111238, "count": 194908, "self": 8.527585226375777, "children": { "process_trajectory": { "total": 392.0611881307559, "count": 194908, "self": 391.43088926775545, "children": { "RLTrainer._checkpoint": { "total": 0.630298863000462, "count": 6, "self": 0.630298863000462 } } }, "_update_policy": { "total": 1523.5693480539921, "count": 1395, "self": 973.411984444172, "children": { "TorchPPOOptimizer.update": { "total": 550.1573636098201, "count": 68412, "self": 550.1573636098201 } } } } } } }, "trainer_threads": { "total": 1.2380005500745028e-06, "count": 1, "self": 1.2380005500745028e-06 }, "TrainerController._save_models": { "total": 0.09773076700003003, "count": 1, "self": 0.0015487860000575893, "children": { "RLTrainer._checkpoint": { "total": 0.09618198099997244, "count": 1, "self": 0.09618198099997244 } } } } } } }