{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6450259685516357, "min": 0.6410074830055237, "max": 1.5322463512420654, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19216.61328125, "min": 19127.6640625, "max": 46482.2265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29952.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22885049879550934, "min": -0.11402715742588043, "max": 0.24656739830970764, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 57.44147491455078, "min": -27.024436950683594, "max": 62.62812042236328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 3.2871368603082374e-05, "min": -0.007853555493056774, "max": 0.1551777571439743, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.008250713348388672, "min": -2.0026566982269287, "max": 36.777130126953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06732209784522031, "min": 0.06732209784522031, "max": 0.07421415945623422, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0098314676783047, "min": 0.49244108266710984, "max": 1.0562169675715265, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008960935817109808, "min": 3.054372120455332e-05, "max": 0.008960935817109808, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13441403725664713, "min": 0.0003970683756591932, "max": 0.13441403725664713, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2378564190973333e-05, "min": 1.2378564190973333e-05, "max": 0.0004919177159021714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001856784628646, "min": 0.0001856784628646, "max": 0.005421213815757299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247569333333334, "min": 0.10247569333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371354000000002, "min": 1.3691136000000002, "max": 2.4842427000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000257321764, "min": 0.000257321764, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00385982646, "min": 0.00385982646, "max": 0.10845584573, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0024546144995838404, "min": 0.0024546144995838404, "max": 0.07493139803409576, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0368192158639431, "min": 0.0354711078107357, "max": 0.5245198011398315, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 687.0666666666667, "min": 660.75, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30918.0, "min": 15984.0, "max": 32179.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7630272400988773, "min": -1.0000000521540642, "max": 0.9755363293330778, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 33.573198564350605, "min": -32.000001668930054, "max": 42.92359849065542, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7630272400988773, "min": -1.0000000521540642, "max": 0.9755363293330778, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 33.573198564350605, "min": -32.000001668930054, "max": 42.92359849065542, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019590981404193866, "min": 0.019441925362116308, "max": 4.322437385097146, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 0.8620031817845302, "min": 0.8554447159331175, "max": 69.15899816155434, "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": "1690026003", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690028497" }, "total": 2493.795741709, "count": 1, "self": 0.4908949479995499, "children": { "run_training.setup": { "total": 0.03342672200051311, "count": 1, "self": 0.03342672200051311 }, "TrainerController.start_learning": { "total": 2493.271420039, "count": 1, "self": 1.538290237860565, "children": { "TrainerController._reset_env": { "total": 5.724531943000329, "count": 1, "self": 5.724531943000329 }, "TrainerController.advance": { "total": 2485.913467538141, "count": 63278, "self": 1.5527100442959636, "children": { "env_step": { "total": 1451.5818918200293, "count": 63278, "self": 1333.24871613504, "children": { "SubprocessEnvManager._take_step": { "total": 117.38603611204053, "count": 63278, "self": 5.157252747841994, "children": { "TorchPolicy.evaluate": { "total": 112.22878336419853, "count": 62561, "self": 112.22878336419853 } } }, "workers": { "total": 0.9471395729487995, "count": 63278, "self": 0.0, "children": { "worker_root": { "total": 2488.0286356773104, "count": 63278, "is_parallel": true, "self": 1277.8358804564432, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003004457999850274, "count": 1, "is_parallel": true, "self": 0.0008506439990014769, "children": { "_process_rank_one_or_two_observation": { "total": 0.002153814000848797, "count": 8, "is_parallel": true, "self": 0.002153814000848797 } } }, "UnityEnvironment.step": { "total": 0.053261887000189745, "count": 1, "is_parallel": true, "self": 0.0005864399972779211, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005664620002789889, "count": 1, "is_parallel": true, "self": 0.0005664620002789889 }, "communicator.exchange": { "total": 0.0501881880009023, "count": 1, "is_parallel": true, "self": 0.0501881880009023 }, "steps_from_proto": { "total": 0.0019207970017305342, "count": 1, "is_parallel": true, "self": 0.0003889070012519369, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015318900004785974, "count": 8, "is_parallel": true, "self": 0.0015318900004785974 } } } } } } }, "UnityEnvironment.step": { "total": 1210.1927552208672, "count": 63277, "is_parallel": true, "self": 35.84065835011279, "children": { "UnityEnvironment._generate_step_input": { "total": 25.53304013212255, "count": 63277, "is_parallel": true, "self": 25.53304013212255 }, "communicator.exchange": { "total": 1037.242527930919, "count": 63277, "is_parallel": true, "self": 1037.242527930919 }, "steps_from_proto": { "total": 111.57652880771275, "count": 63277, "is_parallel": true, "self": 22.968402393804354, "children": { "_process_rank_one_or_two_observation": { "total": 88.6081264139084, "count": 506216, "is_parallel": true, "self": 88.6081264139084 } } } } } } } } } } }, "trainer_advance": { "total": 1032.7788656738157, "count": 63278, "self": 2.669245314771615, "children": { "process_trajectory": { "total": 118.07764391304227, "count": 63278, "self": 117.79136581504281, "children": { "RLTrainer._checkpoint": { "total": 0.2862780979994568, "count": 2, "self": 0.2862780979994568 } } }, "_update_policy": { "total": 912.0319764460019, "count": 439, "self": 596.0920037379474, "children": { "TorchPPOOptimizer.update": { "total": 315.9399727080545, "count": 38105, "self": 315.9399727080545 } } } } } } }, "trainer_threads": { "total": 1.0249987099086866e-06, "count": 1, "self": 1.0249987099086866e-06 }, "TrainerController._save_models": { "total": 0.09512929499942402, "count": 1, "self": 0.0012831679996452294, "children": { "RLTrainer._checkpoint": { "total": 0.09384612699977879, "count": 1, "self": 0.09384612699977879 } } } } } } }