{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5140262246131897, "min": 0.5140262246131897, "max": 1.4391610622406006, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15585.2744140625, "min": 15585.2744140625, "max": 43658.390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989899.0, "min": 29975.0, "max": 989899.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989899.0, "min": 29975.0, "max": 989899.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40128517150878906, "min": -0.09970172494649887, "max": 0.42190641164779663, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.74185180664062, "min": -24.127817153930664, "max": 114.33663940429688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07886388152837753, "min": -0.020522261038422585, "max": 0.3121149241924286, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 20.977792739868164, "min": -5.335787773132324, "max": 75.21969604492188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06832461333501019, "min": 0.06401531374389638, "max": 0.07179197058836248, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9565445866901428, "min": 0.565873657516806, "max": 1.0406451638700673, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018559521576944026, "min": 0.0007753290539792149, "max": 0.018559521576944026, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2598333020772164, "min": 0.010079277701729793, "max": 0.2598333020772164, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.534168917214288e-06, "min": 7.534168917214288e-06, "max": 0.000294765526744825, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010547836484100003, "min": 0.00010547836484100003, "max": 0.0035086580304474, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251135714285713, "min": 0.10251135714285713, "max": 0.198255175, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351589999999999, "min": 1.4351589999999999, "max": 2.5695526000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026088457857142863, "min": 0.00026088457857142863, "max": 0.009825691982499999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003652384100000001, "min": 0.003652384100000001, "max": 0.11697830474, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008880306966602802, "min": 0.008880306966602802, "max": 0.45677196979522705, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12432429939508438, "min": 0.12432429939508438, "max": 3.6541757583618164, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 422.8493150684931, "min": 404.93150684931504, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30868.0, "min": 17541.0, "max": 32625.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3578821723795917, "min": -0.999858116430621, "max": 1.484681057567532, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.1253985837102, "min": -30.99560160934925, "max": 109.86639825999737, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3578821723795917, "min": -0.999858116430621, "max": 1.484681057567532, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.1253985837102, "min": -30.99560160934925, "max": 109.86639825999737, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03866022539505263, "min": 0.03866022539505263, "max": 9.29746906997429, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.822196453838842, "min": 2.666131267826131, "max": 167.35444325953722, "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": "1713524202", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713526421" }, "total": 2219.277005191, "count": 1, "self": 0.5868690130000687, "children": { "run_training.setup": { "total": 0.05304830399995808, "count": 1, "self": 0.05304830399995808 }, "TrainerController.start_learning": { "total": 2218.6370878740004, "count": 1, "self": 1.9633150509744155, "children": { "TrainerController._reset_env": { "total": 2.8526793159999784, "count": 1, "self": 2.8526793159999784 }, "TrainerController.advance": { "total": 2213.762012238026, "count": 63547, "self": 1.8097842970810234, "children": { "env_step": { "total": 1468.5785473689552, "count": 63547, "self": 1339.792102782948, "children": { "SubprocessEnvManager._take_step": { "total": 127.56214935500276, "count": 63547, "self": 4.695721017019139, "children": { "TorchPolicy.evaluate": { "total": 122.86642833798362, "count": 62542, "self": 122.86642833798362 } } }, "workers": { "total": 1.2242952310044188, "count": 63547, "self": 0.0, "children": { "worker_root": { "total": 2214.347077796005, "count": 63547, "is_parallel": true, "self": 1014.8150732889999, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007910960000003797, "count": 1, "is_parallel": true, "self": 0.004439000000047599, "children": { "_process_rank_one_or_two_observation": { "total": 0.003471959999956198, "count": 8, "is_parallel": true, "self": 0.003471959999956198 } } }, "UnityEnvironment.step": { "total": 0.054862544000002345, "count": 1, "is_parallel": true, "self": 0.0006854300000327385, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004128900000068825, "count": 1, "is_parallel": true, "self": 0.0004128900000068825 }, "communicator.exchange": { "total": 0.05200017399999979, "count": 1, "is_parallel": true, "self": 0.05200017399999979 }, "steps_from_proto": { "total": 0.0017640499999629355, "count": 1, "is_parallel": true, "self": 0.0003627499999652173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014012999999977183, "count": 8, "is_parallel": true, "self": 0.0014012999999977183 } } } } } } }, "UnityEnvironment.step": { "total": 1199.5320045070052, "count": 63546, "is_parallel": true, "self": 38.25169981208319, "children": { "UnityEnvironment._generate_step_input": { "total": 19.69471548899321, "count": 63546, "is_parallel": true, "self": 19.69471548899321 }, "communicator.exchange": { "total": 1046.9141536519196, "count": 63546, "is_parallel": true, "self": 1046.9141536519196 }, "steps_from_proto": { "total": 94.67143555400924, "count": 63546, "is_parallel": true, "self": 20.852647415105707, "children": { "_process_rank_one_or_two_observation": { "total": 73.81878813890353, "count": 508368, "is_parallel": true, "self": 73.81878813890353 } } } } } } } } } } }, "trainer_advance": { "total": 743.3736805719893, "count": 63547, "self": 4.151871275003259, "children": { "process_trajectory": { "total": 124.56097160698329, "count": 63547, "self": 124.37023336798308, "children": { "RLTrainer._checkpoint": { "total": 0.19073823900021125, "count": 2, "self": 0.19073823900021125 } } }, "_update_policy": { "total": 614.6608376900028, "count": 455, "self": 244.79770379598511, "children": { "TorchPPOOptimizer.update": { "total": 369.8631338940177, "count": 22815, "self": 369.8631338940177 } } } } } } }, "trainer_threads": { "total": 9.000000318337698e-07, "count": 1, "self": 9.000000318337698e-07 }, "TrainerController._save_models": { "total": 0.059080369000184874, "count": 1, "self": 0.00183022000010169, "children": { "RLTrainer._checkpoint": { "total": 0.057250149000083184, "count": 1, "self": 0.057250149000083184 } } } } } } }