{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47019147872924805, "min": 0.47019147872924805, "max": 1.4967389106750488, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13947.759765625, "min": 13947.759765625, "max": 45405.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49538129568099976, "min": -0.10629834979772568, "max": 0.5803999304771423, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 134.74371337890625, "min": -25.724201202392578, "max": 161.93157958984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01387109886854887, "min": -0.03978590667247772, "max": 0.11708737909793854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7729389667510986, "min": -9.42926025390625, "max": 28.100971221923828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06516321028040785, "min": 0.06516321028040785, "max": 0.0744888767572246, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9122849439257099, "min": 0.5002769117085357, "max": 1.053547180616685, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014955064537519188, "min": 0.0005392633678588749, "max": 0.01625847792907041, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20937090352526863, "min": 0.007010423782165373, "max": 0.23562632080574983, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.258747580449997e-06, "min": 7.258747580449997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010162246612629996, "min": 0.00010162246612629996, "max": 0.0034932868355710997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241955000000004, "min": 0.10241955000000004, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338737000000006, "min": 1.3691136000000002, "max": 2.484064, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025171304500000007, "min": 0.00025171304500000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035239826300000007, "min": 0.0035239826300000007, "max": 0.11645644710999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010213752277195454, "min": 0.010213752277195454, "max": 0.24146492779254913, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1429925262928009, "min": 0.1429925262928009, "max": 1.6902544498443604, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 378.2560975609756, "min": 324.10227272727275, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31017.0, "min": 15984.0, "max": 33128.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4754864027102788, "min": -1.0000000521540642, "max": 1.6758977154439145, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 119.51439861953259, "min": -32.000001668930054, "max": 148.4319978877902, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4754864027102788, "min": -1.0000000521540642, "max": 1.6758977154439145, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 119.51439861953259, "min": -32.000001668930054, "max": 148.4319978877902, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03981199028652397, "min": 0.03493330160894071, "max": 4.9287842540070415, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2247712132084416, "min": 3.062824132866808, "max": 78.86054806411266, "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": "1678708494", "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": "1678710636" }, "total": 2142.3020889259997, "count": 1, "self": 0.8344891609995102, "children": { "run_training.setup": { "total": 0.10071282800004155, "count": 1, "self": 0.10071282800004155 }, "TrainerController.start_learning": { "total": 2141.366886937, "count": 1, "self": 1.328769133944661, "children": { "TrainerController._reset_env": { "total": 5.8561510479999015, "count": 1, "self": 5.8561510479999015 }, "TrainerController.advance": { "total": 2134.021762569055, "count": 63703, "self": 1.3644642280373773, "children": { "env_step": { "total": 1505.0004920089812, "count": 63703, "self": 1397.5307845460097, "children": { "SubprocessEnvManager._take_step": { "total": 106.64765105298943, "count": 63703, "self": 4.593527341959316, "children": { "TorchPolicy.evaluate": { "total": 102.05412371103012, "count": 62561, "self": 102.05412371103012 } } }, "workers": { "total": 0.8220564099819967, "count": 63703, "self": 0.0, "children": { "worker_root": { "total": 2136.6348991780037, "count": 63703, "is_parallel": true, "self": 852.1371668120391, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017750990000422462, "count": 1, "is_parallel": true, "self": 0.0005693850000625389, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012057139999797073, "count": 8, "is_parallel": true, "self": 0.0012057139999797073 } } }, "UnityEnvironment.step": { "total": 0.04507985500003997, "count": 1, "is_parallel": true, "self": 0.0005694600001788785, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045566900007543154, "count": 1, "is_parallel": true, "self": 0.00045566900007543154 }, "communicator.exchange": { "total": 0.04252236299998913, "count": 1, "is_parallel": true, "self": 0.04252236299998913 }, "steps_from_proto": { "total": 0.0015323629997965327, "count": 1, "is_parallel": true, "self": 0.0003359309998813842, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011964319999151485, "count": 8, "is_parallel": true, "self": 0.0011964319999151485 } } } } } } }, "UnityEnvironment.step": { "total": 1284.4977323659646, "count": 63702, "is_parallel": true, "self": 30.77022109893005, "children": { "UnityEnvironment._generate_step_input": { "total": 22.210098435990403, "count": 63702, "is_parallel": true, "self": 22.210098435990403 }, "communicator.exchange": { "total": 1140.1662154540086, "count": 63702, "is_parallel": true, "self": 1140.1662154540086 }, "steps_from_proto": { "total": 91.35119737703553, "count": 63702, "is_parallel": true, "self": 19.329220477013678, "children": { "_process_rank_one_or_two_observation": { "total": 72.02197690002185, "count": 509616, "is_parallel": true, "self": 72.02197690002185 } } } } } } } } } } }, "trainer_advance": { "total": 627.6568063320367, "count": 63703, "self": 2.457332148986552, "children": { "process_trajectory": { "total": 117.24018147905508, "count": 63703, "self": 116.93804312105522, "children": { "RLTrainer._checkpoint": { "total": 0.30213835799986555, "count": 2, "self": 0.30213835799986555 } } }, "_update_policy": { "total": 507.95929270399506, "count": 448, "self": 322.4392480210265, "children": { "TorchPPOOptimizer.update": { "total": 185.52004468296855, "count": 22791, "self": 185.52004468296855 } } } } } } }, "trainer_threads": { "total": 1.3670000953425188e-06, "count": 1, "self": 1.3670000953425188e-06 }, "TrainerController._save_models": { "total": 0.16020281900000555, "count": 1, "self": 0.0020388020002428675, "children": { "RLTrainer._checkpoint": { "total": 0.15816401699976268, "count": 1, "self": 0.15816401699976268 } } } } } } }