{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4658516049385071, "min": 0.45671138167381287, "max": 1.3945306539535522, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13953.1875, "min": 13679.4189453125, "max": 42304.48046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5374999046325684, "min": -0.12221922725439072, "max": 0.6481914520263672, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.19998168945312, "min": -29.454833984375, "max": 186.67913818359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02697666548192501, "min": -0.010488578118383884, "max": 0.6428115367889404, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.337653160095215, "min": -2.8948476314544678, "max": 152.34632873535156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06848114221453007, "min": 0.06410345989978557, "max": 0.07378815947156815, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9587359910034209, "min": 0.5165171163009771, "max": 1.0709164051998719, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017226766320372636, "min": 0.0004595153332782961, "max": 0.018250062832022178, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2411747284852169, "min": 0.006433214665896145, "max": 0.2555008796483105, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.669018872264282e-06, "min": 7.669018872264282e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010736626421169995, "min": 0.00010736626421169995, "max": 0.003507923630692199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255630714285714, "min": 0.10255630714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357883, "min": 1.3886848, "max": 2.5693078, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026537508357142846, "min": 0.00026537508357142846, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037152511699999986, "min": 0.0037152511699999986, "max": 0.11695384922, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011024088598787785, "min": 0.011024088598787785, "max": 0.507912814617157, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15433724224567413, "min": 0.15433724224567413, "max": 3.555389881134033, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 368.97777777777776, "min": 285.7244897959184, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33208.0, "min": 15984.0, "max": 33450.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.58656220510602, "min": -1.0000000521540642, "max": 1.6734700872726047, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.7905984595418, "min": -30.690001651644707, "max": 169.4209976196289, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.58656220510602, "min": -1.0000000521540642, "max": 1.6734700872726047, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.7905984595418, "min": -30.690001651644707, "max": 169.4209976196289, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04225839509551103, "min": 0.034116817707068876, "max": 10.840719440951943, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8032555585959926, "min": 3.377564952999819, "max": 173.4515110552311, "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": "1702271283", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702273526" }, "total": 2242.851679383, "count": 1, "self": 0.47537959500004945, "children": { "run_training.setup": { "total": 0.054695980999895255, "count": 1, "self": 0.054695980999895255 }, "TrainerController.start_learning": { "total": 2242.321603807, "count": 1, "self": 1.4648482760640036, "children": { "TrainerController._reset_env": { "total": 4.455949815999929, "count": 1, "self": 4.455949815999929 }, "TrainerController.advance": { "total": 2236.3170403299364, "count": 63871, "self": 1.4621552099506516, "children": { "env_step": { "total": 1591.8575832019922, "count": 63871, "self": 1452.285034374962, "children": { "SubprocessEnvManager._take_step": { "total": 138.6884541040306, "count": 63871, "self": 4.852713030096538, "children": { "TorchPolicy.evaluate": { "total": 133.83574107393406, "count": 62562, "self": 133.83574107393406 } } }, "workers": { "total": 0.8840947229996345, "count": 63871, "self": 0.0, "children": { "worker_root": { "total": 2237.3830649530237, "count": 63871, "is_parallel": true, "self": 906.6933248699754, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0065183199999410135, "count": 1, "is_parallel": true, "self": 0.004691858000342108, "children": { "_process_rank_one_or_two_observation": { "total": 0.001826461999598905, "count": 8, "is_parallel": true, "self": 0.001826461999598905 } } }, "UnityEnvironment.step": { "total": 0.04922627900009502, "count": 1, "is_parallel": true, "self": 0.0005736830000842019, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004720849999557686, "count": 1, "is_parallel": true, "self": 0.0004720849999557686 }, "communicator.exchange": { "total": 0.046570059000032415, "count": 1, "is_parallel": true, "self": 0.046570059000032415 }, "steps_from_proto": { "total": 0.001610452000022633, "count": 1, "is_parallel": true, "self": 0.00034617000005709997, "children": { "_process_rank_one_or_two_observation": { "total": 0.001264281999965533, "count": 8, "is_parallel": true, "self": 0.001264281999965533 } } } } } } }, "UnityEnvironment.step": { "total": 1330.6897400830483, "count": 63870, "is_parallel": true, "self": 34.095182896032384, "children": { "UnityEnvironment._generate_step_input": { "total": 24.663983939007267, "count": 63870, "is_parallel": true, "self": 24.663983939007267 }, "communicator.exchange": { "total": 1171.793192376019, "count": 63870, "is_parallel": true, "self": 1171.793192376019 }, "steps_from_proto": { "total": 100.13738087198954, "count": 63870, "is_parallel": true, "self": 20.395226248049084, "children": { "_process_rank_one_or_two_observation": { "total": 79.74215462394045, "count": 510960, "is_parallel": true, "self": 79.74215462394045 } } } } } } } } } } }, "trainer_advance": { "total": 642.9973019179934, "count": 63871, "self": 2.7402156839821146, "children": { "process_trajectory": { "total": 128.59139278800785, "count": 63871, "self": 128.41265950500838, "children": { "RLTrainer._checkpoint": { "total": 0.17873328299947389, "count": 2, "self": 0.17873328299947389 } } }, "_update_policy": { "total": 511.6656934460034, "count": 448, "self": 308.21561246801843, "children": { "TorchPPOOptimizer.update": { "total": 203.45008097798495, "count": 22839, "self": 203.45008097798495 } } } } } } }, "trainer_threads": { "total": 8.600000001024455e-07, "count": 1, "self": 8.600000001024455e-07 }, "TrainerController._save_models": { "total": 0.08376452499987863, "count": 1, "self": 0.0013615729999401083, "children": { "RLTrainer._checkpoint": { "total": 0.08240295199993852, "count": 1, "self": 0.08240295199993852 } } } } } } }