{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3351125419139862, "min": 0.33189326524734497, "max": 1.3687214851379395, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 9999.7578125, "min": 9999.7578125, "max": 41521.53515625, "count": 36 }, "Pyramids.Step.mean": { "value": 1079885.0, "min": 29952.0, "max": 1079885.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079885.0, "min": 29952.0, "max": 1079885.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5350074768066406, "min": -0.1271953284740448, "max": 0.5919860005378723, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.80209350585938, "min": -30.65407371520996, "max": 164.57211303710938, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -6.175429734867066e-05, "min": -0.003601330565288663, "max": 0.557278573513031, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.017291203141212463, "min": -0.9615552425384521, "max": 132.0750274658203, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07049346391743581, "min": 0.06508563713325319, "max": 0.07421449852157748, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9869084948441014, "min": 0.49815960878595955, "max": 1.0582415502662221, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017931372663172494, "min": 0.000523692418971514, "max": 0.017931372663172494, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2510392172844149, "min": 0.005889258294078983, "max": 0.25247206898833, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.598129268188314e-06, "min": 9.598129268188314e-06, "max": 0.00029559148198898697, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001343738097546364, "min": 0.0001343738097546364, "max": 0.0033139177408153626, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10319934415584417, "min": 0.10319934415584417, "max": 0.19853049350649352, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4447908181818183, "min": 1.3719214545454548, "max": 2.436768545454546, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.0003296144811688314, "min": 0.0003296144811688314, "max": 0.009853196301298703, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.004614602736363639, "min": 0.004614602736363639, "max": 0.11048345426363637, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010285355150699615, "min": 0.010285355150699615, "max": 0.5733075141906738, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14399497210979462, "min": 0.14399497210979462, "max": 4.013152599334717, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 331.51724137931035, "min": 301.80392156862746, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28842.0, "min": 15984.0, "max": 33187.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5765080299528165, "min": -1.0000000521540642, "max": 1.6197450746800386, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.15619860589504, "min": -32.000001668930054, "max": 165.21399761736393, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5765080299528165, "min": -1.0000000521540642, "max": 1.6197450746800386, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.15619860589504, "min": -32.000001668930054, "max": 165.21399761736393, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.034637269224093735, "min": 0.034637269224093735, "max": 11.035581363365054, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 3.013442422496155, "min": 3.013442422496155, "max": 176.56930181384087, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1751450074", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751452448" }, "total": 2373.423566798, "count": 1, "self": 0.5523976770000445, "children": { "run_training.setup": { "total": 0.02284334499995566, "count": 1, "self": 0.02284334499995566 }, "TrainerController.start_learning": { "total": 2372.848325776, "count": 1, "self": 1.3416274809360402, "children": { "TrainerController._reset_env": { "total": 3.890055951000022, "count": 1, "self": 3.890055951000022 }, "TrainerController.advance": { "total": 2367.537731608064, "count": 70298, "self": 1.427440480084897, "children": { "env_step": { "total": 1662.0997267000585, "count": 70298, "self": 1508.462816020221, "children": { "SubprocessEnvManager._take_step": { "total": 152.82532726194518, "count": 70298, "self": 4.692824763930048, "children": { "TorchPolicy.evaluate": { "total": 148.13250249801513, "count": 68816, "self": 148.13250249801513 } } }, "workers": { "total": 0.8115834178922796, "count": 70298, "self": 0.0, "children": { "worker_root": { "total": 2368.01490010601, "count": 70298, "is_parallel": true, "self": 975.1422123020211, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005240819999926316, "count": 1, "is_parallel": true, "self": 0.004013396000118519, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012274239998077974, "count": 8, "is_parallel": true, "self": 0.0012274239998077974 } } }, "UnityEnvironment.step": { "total": 0.044480287999931534, "count": 1, "is_parallel": true, "self": 0.0005436209999061248, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043691599989870156, "count": 1, "is_parallel": true, "self": 0.00043691599989870156 }, "communicator.exchange": { "total": 0.0419874480000999, "count": 1, "is_parallel": true, "self": 0.0419874480000999 }, "steps_from_proto": { "total": 0.0015123030000268045, "count": 1, "is_parallel": true, "self": 0.00031563400034428923, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011966689996825153, "count": 8, "is_parallel": true, "self": 0.0011966689996825153 } } } } } } }, "UnityEnvironment.step": { "total": 1392.8726878039888, "count": 70297, "is_parallel": true, "self": 34.7834155749797, "children": { "UnityEnvironment._generate_step_input": { "total": 23.95798807803817, "count": 70297, "is_parallel": true, "self": 23.95798807803817 }, "communicator.exchange": { "total": 1234.2793065009193, "count": 70297, "is_parallel": true, "self": 1234.2793065009193 }, "steps_from_proto": { "total": 99.8519776500516, "count": 70297, "is_parallel": true, "self": 19.74388415385033, "children": { "_process_rank_one_or_two_observation": { "total": 80.10809349620126, "count": 562376, "is_parallel": true, "self": 80.10809349620126 } } } } } } } } } } }, "trainer_advance": { "total": 704.0105644279206, "count": 70298, "self": 2.664951175861006, "children": { "process_trajectory": { "total": 132.58748609605618, "count": 70298, "self": 132.28952762105655, "children": { "RLTrainer._checkpoint": { "total": 0.297958474999632, "count": 2, "self": 0.297958474999632 } } }, "_update_policy": { "total": 568.7581271560034, "count": 486, "self": 315.7641164870072, "children": { "TorchPPOOptimizer.update": { "total": 252.99401066899622, "count": 25140, "self": 252.99401066899622 } } } } } } }, "trainer_threads": { "total": 8.590000106778461e-07, "count": 1, "self": 8.590000106778461e-07 }, "TrainerController._save_models": { "total": 0.0789098769996599, "count": 1, "self": 0.0012257319999662286, "children": { "RLTrainer._checkpoint": { "total": 0.07768414499969367, "count": 1, "self": 0.07768414499969367 } } } } } } }