{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2850606441497803, "min": 0.2850606441497803, "max": 1.4549331665039062, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8570.0634765625, "min": 8570.0634765625, "max": 44136.8515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989960.0, "min": 29936.0, "max": 989960.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989960.0, "min": 29936.0, "max": 989960.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6157785654067993, "min": -0.2300759255886078, "max": 0.6157785654067993, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.80221557617188, "min": -54.75807189941406, "max": 171.80221557617188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006526252720504999, "min": -0.0025858799926936626, "max": 0.5017464756965637, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8208245038986206, "min": -0.7343899011611938, "max": 119.41566467285156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751514978426233, "min": 0.06473264137706237, "max": 0.07424198217387411, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9452120969796726, "min": 0.4879827787286747, "max": 1.0570276620633463, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013204971776817209, "min": 0.0010211280794210785, "max": 0.01827282625279395, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18486960487544093, "min": 0.01327466503247402, "max": 0.2265255921702905, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.380633254107147e-06, "min": 7.380633254107147e-06, "max": 0.0002952336015888, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010332886555750006, "min": 0.00010332886555750006, "max": 0.0036348160883947, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246017857142857, "min": 0.10246017857142857, "max": 0.19841119999999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344425, "min": 1.3888783999999998, "max": 2.611605300000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002557718392857145, "min": 0.0002557718392857145, "max": 0.009841278879999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003580805750000003, "min": 0.003580805750000003, "max": 0.12117936947, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014204681850969791, "min": 0.014204681850969791, "max": 0.6670668721199036, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19886554777622223, "min": 0.19886554777622223, "max": 4.669467926025391, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 323.97777777777776, "min": 318.88659793814435, "max": 994.1290322580645, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29158.0, "min": 17118.0, "max": 32921.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6512898628631334, "min": -0.8659677964545065, "max": 1.6604886503563714, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 146.96479779481888, "min": -26.845001690089703, "max": 161.06739908456802, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6512898628631334, "min": -0.8659677964545065, "max": 1.6604886503563714, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 146.96479779481888, "min": -26.845001690089703, "max": 161.06739908456802, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047866596891335475, "min": 0.047866596891335475, "max": 13.375689694450962, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.260127123328857, "min": 4.260127123328857, "max": 240.7624145001173, "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": "1679700791", "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": "1679703095" }, "total": 2304.013763954, "count": 1, "self": 0.8000883119998434, "children": { "run_training.setup": { "total": 0.10927096400018854, "count": 1, "self": 0.10927096400018854 }, "TrainerController.start_learning": { "total": 2303.104404678, "count": 1, "self": 1.6061935609732245, "children": { "TrainerController._reset_env": { "total": 7.191205973000024, "count": 1, "self": 7.191205973000024 }, "TrainerController.advance": { "total": 2294.1603502940266, "count": 63936, "self": 1.708674820024953, "children": { "env_step": { "total": 1633.6623783440214, "count": 63936, "self": 1511.3710944750628, "children": { "SubprocessEnvManager._take_step": { "total": 121.3093568119516, "count": 63936, "self": 5.279877075915238, "children": { "TorchPolicy.evaluate": { "total": 116.02947973603636, "count": 62568, "self": 116.02947973603636 } } }, "workers": { "total": 0.981927057006942, "count": 63936, "self": 0.0, "children": { "worker_root": { "total": 2297.1041579629805, "count": 63936, "is_parallel": true, "self": 914.7469910429681, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002565086999993582, "count": 1, "is_parallel": true, "self": 0.0008018669996090466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017632200003845355, "count": 8, "is_parallel": true, "self": 0.0017632200003845355 } } }, "UnityEnvironment.step": { "total": 0.047035330999960934, "count": 1, "is_parallel": true, "self": 0.0005415480000010575, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005027439999594208, "count": 1, "is_parallel": true, "self": 0.0005027439999594208 }, "communicator.exchange": { "total": 0.04432649299997138, "count": 1, "is_parallel": true, "self": 0.04432649299997138 }, "steps_from_proto": { "total": 0.0016645460000290768, "count": 1, "is_parallel": true, "self": 0.0003791359997649124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012854100002641644, "count": 8, "is_parallel": true, "self": 0.0012854100002641644 } } } } } } }, "UnityEnvironment.step": { "total": 1382.3571669200123, "count": 63935, "is_parallel": true, "self": 31.959368816977076, "children": { "UnityEnvironment._generate_step_input": { "total": 24.360976764018687, "count": 63935, "is_parallel": true, "self": 24.360976764018687 }, "communicator.exchange": { "total": 1226.9404408910277, "count": 63935, "is_parallel": true, "self": 1226.9404408910277 }, "steps_from_proto": { "total": 99.09638044798885, "count": 63935, "is_parallel": true, "self": 21.68372778399089, "children": { "_process_rank_one_or_two_observation": { "total": 77.41265266399796, "count": 511480, "is_parallel": true, "self": 77.41265266399796 } } } } } } } } } } }, "trainer_advance": { "total": 658.78929712998, "count": 63936, "self": 2.9694343249700523, "children": { "process_trajectory": { "total": 126.93954239100731, "count": 63936, "self": 126.68060574600713, "children": { "RLTrainer._checkpoint": { "total": 0.2589366450001762, "count": 2, "self": 0.2589366450001762 } } }, "_update_policy": { "total": 528.8803204140027, "count": 460, "self": 338.208335945983, "children": { "TorchPPOOptimizer.update": { "total": 190.67198446801967, "count": 22788, "self": 190.67198446801967 } } } } } } }, "trainer_threads": { "total": 1.5380001059384085e-06, "count": 1, "self": 1.5380001059384085e-06 }, "TrainerController._save_models": { "total": 0.14665331200012588, "count": 1, "self": 0.0018620229998305149, "children": { "RLTrainer._checkpoint": { "total": 0.14479128900029536, "count": 1, "self": 0.14479128900029536 } } } } } } }