{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.20909874141216278, "min": 0.1949726790189743, "max": 0.24659718573093414, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 6363.29296875, "min": 2694.81396484375, "max": 7389.0244140625, "count": 20 }, "Pyramids.Step.mean": { "value": 1979953.0, "min": 1409898.0, "max": 1979953.0, "count": 20 }, "Pyramids.Step.sum": { "value": 1979953.0, "min": 1409898.0, "max": 1979953.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7426161766052246, "min": 0.6558880805969238, "max": 0.8424283862113953, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 225.0126953125, "min": 61.653480529785156, "max": 255.25579833984375, "count": 20 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031264528632164, "min": -0.05216704681515694, "max": 0.03963925316929817, "count": 20 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.473152160644531, "min": -6.927762985229492, "max": 12.010693550109863, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 240.27777777777777, "min": 223.68702290076337, "max": 288.92727272727274, "count": 20 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30275.0, "min": 9309.0, "max": 31782.0, "count": 20 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7597222077468084, "min": 1.6378581649877808, "max": 1.7625564401668887, "count": 20 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 221.72499817609787, "min": 66.69099980592728, "max": 231.65419852733612, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7597222077468084, "min": 1.6378581649877808, "max": 1.7625564401668887, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 221.72499817609787, "min": 66.69099980592728, "max": 231.65419852733612, "count": 20 }, "Pyramids.Policy.RndReward.mean": { "value": 0.022153528766278806, "min": 0.02162928428235598, "max": 0.027806597438228147, "count": 20 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7913446245511295, "min": 0.9904941387940198, "max": 3.175016888548271, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06888369233994228, "min": 0.06337500430527142, "max": 0.071930860919858, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0332553850991342, "min": 0.25350001722108567, "max": 1.0703795793096478, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016365280428565006, "min": 0.012337401918083735, "max": 0.016365280428565006, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24547920642847507, "min": 0.0563335788998908, "max": 0.24547920642847507, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.23815825398e-06, "min": 5.23815825398e-06, "max": 8.919888276706249e-05, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.857237380970001e-05, "min": 7.857237380970001e-05, "max": 0.0012264580911809997, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10000000000000002, "min": 0.09999999999999999, "max": 0.10000000000000002, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5000000000000002, "min": 0.39999999999999997, "max": 1.5000000000000002, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018442739800000004, "min": 0.00018442739800000004, "max": 0.00298032045625, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.0027664109700000004, "min": 0.0027664109700000004, "max": 0.040991018100000005, "count": 20 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008875912055373192, "min": 0.00887424685060978, "max": 0.01034853607416153, "count": 20 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13313868641853333, "min": 0.04139414429664612, "max": 0.14527718722820282, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679234727", "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=PyramidsTraining2 --no-graphics --resume", "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": "1679236316" }, "total": 1589.0462459160008, "count": 1, "self": 0.9361756820035225, "children": { "run_training.setup": { "total": 0.16557168299914338, "count": 1, "self": 0.16557168299914338 }, "TrainerController.start_learning": { "total": 1587.944498550998, "count": 1, "self": 1.0365882107980724, "children": { "TrainerController._reset_env": { "total": 7.150129449000815, "count": 1, "self": 7.150129449000815 }, "TrainerController.advance": { "total": 1579.6126246852, "count": 39434, "self": 1.1137139180646045, "children": { "env_step": { "total": 1202.8060823790947, "count": 39434, "self": 1129.4289378840622, "children": { "SubprocessEnvManager._take_step": { "total": 72.75138907831933, "count": 39434, "self": 3.1832067811119487, "children": { "TorchPolicy.evaluate": { "total": 69.56818229720739, "count": 37556, "self": 69.56818229720739 } } }, "workers": { "total": 0.6257554167132184, "count": 39434, "self": 0.0, "children": { "worker_root": { "total": 1584.1774843564708, "count": 39434, "is_parallel": true, "self": 533.6017628228074, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024970970007416327, "count": 1, "is_parallel": true, "self": 0.0008042749977903441, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016928220029512886, "count": 8, "is_parallel": true, "self": 0.0016928220029512886 } } }, "UnityEnvironment.step": { "total": 0.04806376800115686, "count": 1, "is_parallel": true, "self": 0.0004168249979557004, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004748860010295175, "count": 1, "is_parallel": true, "self": 0.0004748860010295175 }, "communicator.exchange": { "total": 0.04548206400068011, "count": 1, "is_parallel": true, "self": 0.04548206400068011 }, "steps_from_proto": { "total": 0.0016899930014915299, "count": 1, "is_parallel": true, "self": 0.0003765340043173637, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013134589971741661, "count": 8, "is_parallel": true, "self": 0.0013134589971741661 } } } } } } }, "UnityEnvironment.step": { "total": 1050.5757215336635, "count": 39433, "is_parallel": true, "self": 19.780520651271218, "children": { "UnityEnvironment._generate_step_input": { "total": 13.942504169412132, "count": 39433, "is_parallel": true, "self": 13.942504169412132 }, "communicator.exchange": { "total": 958.0191729879116, "count": 39433, "is_parallel": true, "self": 958.0191729879116 }, "steps_from_proto": { "total": 58.83352372506852, "count": 39433, "is_parallel": true, "self": 13.165210859067884, "children": { "_process_rank_one_or_two_observation": { "total": 45.66831286600063, "count": 315464, "is_parallel": true, "self": 45.66831286600063 } } } } } } } } } } }, "trainer_advance": { "total": 375.69282838804065, "count": 39434, "self": 2.0418972687511996, "children": { "process_trajectory": { "total": 75.66356935731892, "count": 39434, "self": 75.40873285131966, "children": { "RLTrainer._checkpoint": { "total": 0.2548365059992648, "count": 2, "self": 0.2548365059992648 } } }, "_update_policy": { "total": 297.98736176197053, "count": 284, "self": 188.19357864699487, "children": { "TorchPPOOptimizer.update": { "total": 109.79378311497567, "count": 13665, "self": 109.79378311497567 } } } } } } }, "trainer_threads": { "total": 1.3930002751294523e-06, "count": 1, "self": 1.3930002751294523e-06 }, "TrainerController._save_models": { "total": 0.14515481299895328, "count": 1, "self": 0.002944859996205196, "children": { "RLTrainer._checkpoint": { "total": 0.14220995300274808, "count": 1, "self": 0.14220995300274808 } } } } } } }