{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9535247087478638, "min": 0.8795027136802673, "max": 1.4149088859558105, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 28727.79296875, "min": 26131.78515625, "max": 42922.67578125, "count": 10 }, "Pyramids.Step.mean": { "value": 299872.0, "min": 29952.0, "max": 299872.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299872.0, "min": 29952.0, "max": 299872.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06667070090770721, "min": -0.11189569532871246, "max": -0.02967687137424946, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -16.067638397216797, "min": -26.51927947998047, "max": -7.152125835418701, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0362769179046154, "min": 0.03270404040813446, "max": 0.49909767508506775, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.74273681640625, "min": 7.9143781661987305, "max": 118.28614807128906, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06781052923953704, "min": 0.06764780172934738, "max": 0.07334988925752059, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9493474093535185, "min": 0.4964557273360905, "max": 0.9675367218420037, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0008843590397803354, "min": 0.00039062671883247557, "max": 0.006460551510393824, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.012381026556924695, "min": 0.0031250137506598046, "max": 0.05666865131695802, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002715929880404357, "min": 0.0002715929880404357, "max": 0.00029838354339596195, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0038023018325660995, "min": 0.0020691136102954665, "max": 0.004011566162811299, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19053099285714287, "min": 0.19053099285714287, "max": 0.19946118095238097, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.6674339000000002, "min": 1.3897045333333333, "max": 2.7371887000000004, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.009054046186428568, "min": 0.009054046186428568, "max": 0.009946171977142856, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.12675664660999997, "min": 0.06897148288, "max": 0.13372515113, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.034076567739248276, "min": 0.033556122332811356, "max": 0.4852840006351471, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.47707194089889526, "min": 0.4697857201099396, "max": 3.3969879150390625, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 966.28125, "min": 953.125, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30921.0, "min": 15984.0, "max": 31968.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7860545947244673, "min": -1.0000000521540642, "max": -0.6489936007607368, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -25.93980162590742, "min": -32.000001668930054, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7860545947244673, "min": -1.0000000521540642, "max": -0.6489936007607368, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -25.93980162590742, "min": -32.000001668930054, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.33792408513413236, "min": 0.33792408513413236, "max": 9.511274791322649, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 11.151494809426367, "min": 9.63493388146162, "max": 152.18039666116238, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677691898", "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": "1.22.4", "end_time_seconds": "1677692538" }, "total": 640.166973934, "count": 1, "self": 0.3103355840000859, "children": { "run_training.setup": { "total": 0.11844189099997493, "count": 1, "self": 0.11844189099997493 }, "TrainerController.start_learning": { "total": 639.7381964589999, "count": 1, "self": 0.38428136099219046, "children": { "TrainerController._reset_env": { "total": 7.387009753000029, "count": 1, "self": 7.387009753000029 }, "TrainerController.advance": { "total": 631.800660978008, "count": 19107, "self": 0.42453663101241546, "children": { "env_step": { "total": 398.3269726760211, "count": 19107, "self": 364.5513235010426, "children": { "SubprocessEnvManager._take_step": { "total": 33.52683534298353, "count": 19107, "self": 1.4177483869723346, "children": { "TorchPolicy.evaluate": { "total": 32.1090869560112, "count": 18982, "self": 11.043562553977608, "children": { "TorchPolicy.sample_actions": { "total": 21.06552440203359, "count": 18982, "self": 21.06552440203359 } } } } }, "workers": { "total": 0.24881383199499396, "count": 19106, "self": 0.0, "children": { "worker_root": { "total": 638.1549685680018, "count": 19106, "is_parallel": true, "self": 307.3473094819758, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019403060000513506, "count": 1, "is_parallel": true, "self": 0.0007434450001255755, "children": { "_process_rank_one_or_two_observation": { "total": 0.001196860999925775, "count": 8, "is_parallel": true, "self": 0.001196860999925775 } } }, "UnityEnvironment.step": { "total": 0.07139854000001833, "count": 1, "is_parallel": true, "self": 0.0005576920000294194, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005439990000013495, "count": 1, "is_parallel": true, "self": 0.0005439990000013495 }, "communicator.exchange": { "total": 0.06869150700003956, "count": 1, "is_parallel": true, "self": 0.06869150700003956 }, "steps_from_proto": { "total": 0.0016053419999479956, "count": 1, "is_parallel": true, "self": 0.00040270400018016517, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012026379997678305, "count": 8, "is_parallel": true, "self": 0.0012026379997678305 } } } } } } }, "UnityEnvironment.step": { "total": 330.807659086026, "count": 19105, "is_parallel": true, "self": 9.610880126070697, "children": { "UnityEnvironment._generate_step_input": { "total": 7.144477461982206, "count": 19105, "is_parallel": true, "self": 7.144477461982206 }, "communicator.exchange": { "total": 285.77171495198036, "count": 19105, "is_parallel": true, "self": 285.77171495198036 }, "steps_from_proto": { "total": 28.28058654599272, "count": 19105, "is_parallel": true, "self": 6.59945192397231, "children": { "_process_rank_one_or_two_observation": { "total": 21.68113462202041, "count": 152840, "is_parallel": true, "self": 21.68113462202041 } } } } } } } } } } }, "trainer_advance": { "total": 233.04915167097442, "count": 19106, "self": 0.6324331279897706, "children": { "process_trajectory": { "total": 48.94100554298302, "count": 19106, "self": 48.94100554298302 }, "_update_policy": { "total": 183.47571300000163, "count": 119, "self": 70.651754846014, "children": { "TorchPPOOptimizer.update": { "total": 112.82395815398763, "count": 6957, "self": 112.82395815398763 } } } } } } }, "trainer_threads": { "total": 1.5499999790336005e-06, "count": 1, "self": 1.5499999790336005e-06 }, "TrainerController._save_models": { "total": 0.16624281699978383, "count": 1, "self": 0.0019490769996082236, "children": { "RLTrainer._checkpoint": { "total": 0.1642937400001756, "count": 1, "self": 0.1642937400001756 } } } } } } }