{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4975653886795044, "min": 0.47961491346359253, "max": 1.3951681852340698, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14847.3515625, "min": 14350.078125, "max": 42323.8203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4085873067378998, "min": -0.08974519371986389, "max": 0.4677356481552124, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.275634765625, "min": -21.449100494384766, "max": 127.2240982055664, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014104614965617657, "min": -0.005268337205052376, "max": 0.25343790650367737, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.737722873687744, "min": -1.4066460132598877, "max": 60.064781188964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06710505671061397, "min": 0.06500589805137781, "max": 0.07254626382824657, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9394707939485956, "min": 0.5075860991809736, "max": 1.0320246177531465, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01582775835001793, "min": 0.0003489376471918086, "max": 0.01644820867449097, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.221588616900251, "min": 0.004885127060685321, "max": 0.24672313011736455, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.363468974114286e-06, "min": 7.363468974114286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001030885656376, "min": 0.0001030885656376, "max": 0.0036331561889480003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245445714285714, "min": 0.10245445714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343624, "min": 1.3886848, "max": 2.6110519999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025520026857142863, "min": 0.00025520026857142863, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003572803760000001, "min": 0.003572803760000001, "max": 0.12112409480000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009822138585150242, "min": 0.009822138585150242, "max": 0.4139936566352844, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13750994205474854, "min": 0.13750994205474854, "max": 2.8979556560516357, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 389.09859154929575, "min": 389.09859154929575, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27626.0, "min": 15984.0, "max": 32785.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4136591310232458, "min": -1.0000000521540642, "max": 1.5503628332700048, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 100.36979830265045, "min": -29.89840167760849, "max": 108.52539832890034, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4136591310232458, "min": -1.0000000521540642, "max": 1.5503628332700048, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 100.36979830265045, "min": -29.89840167760849, "max": 108.52539832890034, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03946737707309707, "min": 0.03946737707309707, "max": 8.436937988270074, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.802183772189892, "min": 2.802183772189892, "max": 134.9910078123212, "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": "1679827432", "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-01 --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": "1679829642" }, "total": 2209.582941508, "count": 1, "self": 0.48784612800000104, "children": { "run_training.setup": { "total": 0.11024874600002477, "count": 1, "self": 0.11024874600002477 }, "TrainerController.start_learning": { "total": 2208.984846634, "count": 1, "self": 1.6394397359608774, "children": { "TrainerController._reset_env": { "total": 6.252175113000021, "count": 1, "self": 6.252175113000021 }, "TrainerController.advance": { "total": 2200.9970362320387, "count": 63574, "self": 1.7514847370725874, "children": { "env_step": { "total": 1559.8176929829783, "count": 63574, "self": 1442.1477295419309, "children": { "SubprocessEnvManager._take_step": { "total": 116.75630156701459, "count": 63574, "self": 4.92620027300444, "children": { "TorchPolicy.evaluate": { "total": 111.83010129401015, "count": 62556, "self": 111.83010129401015 } } }, "workers": { "total": 0.9136618740329823, "count": 63574, "self": 0.0, "children": { "worker_root": { "total": 2203.9800220379916, "count": 63574, "is_parallel": true, "self": 886.5983430489539, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001865398000006735, "count": 1, "is_parallel": true, "self": 0.0005853390000538639, "children": { "_process_rank_one_or_two_observation": { "total": 0.001280058999952871, "count": 8, "is_parallel": true, "self": 0.001280058999952871 } } }, "UnityEnvironment.step": { "total": 0.08041903200000888, "count": 1, "is_parallel": true, "self": 0.0005801249999421998, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004834540000047127, "count": 1, "is_parallel": true, "self": 0.0004834540000047127 }, "communicator.exchange": { "total": 0.07765766700003951, "count": 1, "is_parallel": true, "self": 0.07765766700003951 }, "steps_from_proto": { "total": 0.001697786000022461, "count": 1, "is_parallel": true, "self": 0.0004786699998930999, "children": { "_process_rank_one_or_two_observation": { "total": 0.001219116000129361, "count": 8, "is_parallel": true, "self": 0.001219116000129361 } } } } } } }, "UnityEnvironment.step": { "total": 1317.3816789890377, "count": 63573, "is_parallel": true, "self": 32.843421338983035, "children": { "UnityEnvironment._generate_step_input": { "total": 23.393729668981848, "count": 63573, "is_parallel": true, "self": 23.393729668981848 }, "communicator.exchange": { "total": 1164.2905567070488, "count": 63573, "is_parallel": true, "self": 1164.2905567070488 }, "steps_from_proto": { "total": 96.85397127402388, "count": 63573, "is_parallel": true, "self": 20.916294354970887, "children": { "_process_rank_one_or_two_observation": { "total": 75.93767691905299, "count": 508584, "is_parallel": true, "self": 75.93767691905299 } } } } } } } } } } }, "trainer_advance": { "total": 639.427858511988, "count": 63574, "self": 2.9213153139994574, "children": { "process_trajectory": { "total": 119.87786565599055, "count": 63574, "self": 119.61185070899074, "children": { "RLTrainer._checkpoint": { "total": 0.2660149469998032, "count": 2, "self": 0.2660149469998032 } } }, "_update_policy": { "total": 516.6286775419981, "count": 452, "self": 327.54881674702926, "children": { "TorchPPOOptimizer.update": { "total": 189.0798607949688, "count": 22830, "self": 189.0798607949688 } } } } } } }, "trainer_threads": { "total": 1.0280000424245372e-06, "count": 1, "self": 1.0280000424245372e-06 }, "TrainerController._save_models": { "total": 0.09619452500010084, "count": 1, "self": 0.001404715000262513, "children": { "RLTrainer._checkpoint": { "total": 0.09478980999983833, "count": 1, "self": 0.09478980999983833 } } } } } } }