{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3801942765712738, "min": 0.3531356751918793, "max": 1.4276145696640015, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11478.8251953125, "min": 10492.3671875, "max": 43308.1171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5224593877792358, "min": -0.09584258496761322, "max": 0.68194580078125, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.76617431640625, "min": -23.223289489746094, "max": 198.44622802734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.001816640025936067, "min": 0.001816640025936067, "max": 0.6472456455230713, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5068425536155701, "min": 0.5068425536155701, "max": 153.397216796875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06956627330648536, "min": 0.06519799841038765, "max": 0.0730428424058857, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.973927826290795, "min": 0.4954061816622444, "max": 1.0871616466365772, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017839861827572655, "min": 0.00040312768468195667, "max": 0.018584341096640047, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24975806558601718, "min": 0.004434404531501524, "max": 0.2787651164496007, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.232369017814287e-06, "min": 7.232369017814287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010125316624940002, "min": 0.00010125316624940002, "max": 0.0035089355303548992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241075714285715, "min": 0.10241075714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337506, "min": 1.3886848, "max": 2.5696451, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002508346385714286, "min": 0.0002508346385714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035116849400000007, "min": 0.0035116849400000007, "max": 0.11698754549000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013090507127344608, "min": 0.013090507127344608, "max": 0.6112498641014099, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18326710164546967, "min": 0.18326710164546967, "max": 4.278748989105225, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.18888888888887, "min": 255.85046728971963, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31607.0, "min": 15984.0, "max": 32621.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.514642683893777, "min": -1.0000000521540642, "max": 1.7266166480603042, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.80319886654615, "min": -31.998401671648026, "max": 186.47459799051285, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.514642683893777, "min": -1.0000000521540642, "max": 1.7266166480603042, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.80319886654615, "min": -31.998401671648026, "max": 186.47459799051285, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047070560233570695, "min": 0.0411717245186554, "max": 12.333260266110301, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.189279860787792, "min": 4.189279860787792, "max": 197.33216425776482, "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": "1679759132", "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": "1679761516" }, "total": 2384.3954895579996, "count": 1, "self": 0.4793556029994761, "children": { "run_training.setup": { "total": 0.20132658300008188, "count": 1, "self": 0.20132658300008188 }, "TrainerController.start_learning": { "total": 2383.714807372, "count": 1, "self": 1.6177493009854516, "children": { "TrainerController._reset_env": { "total": 6.340245222000249, "count": 1, "self": 6.340245222000249 }, "TrainerController.advance": { "total": 2375.6573717840142, "count": 64136, "self": 1.6464778620638754, "children": { "env_step": { "total": 1722.4459355509834, "count": 64136, "self": 1601.9117928129394, "children": { "SubprocessEnvManager._take_step": { "total": 119.5474888199833, "count": 64136, "self": 5.079077506954036, "children": { "TorchPolicy.evaluate": { "total": 114.46841131302926, "count": 62566, "self": 114.46841131302926 } } }, "workers": { "total": 0.9866539180607106, "count": 64136, "self": 0.0, "children": { "worker_root": { "total": 2377.974952608998, "count": 64136, "is_parallel": true, "self": 902.1959823460984, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019545959999049956, "count": 1, "is_parallel": true, "self": 0.0005675769994013535, "children": { "_process_rank_one_or_two_observation": { "total": 0.001387019000503642, "count": 8, "is_parallel": true, "self": 0.001387019000503642 } } }, "UnityEnvironment.step": { "total": 0.04948256699981357, "count": 1, "is_parallel": true, "self": 0.000540748999810603, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005027580000387388, "count": 1, "is_parallel": true, "self": 0.0005027580000387388 }, "communicator.exchange": { "total": 0.046842109999943204, "count": 1, "is_parallel": true, "self": 0.046842109999943204 }, "steps_from_proto": { "total": 0.0015969500000210246, "count": 1, "is_parallel": true, "self": 0.000352962999841111, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012439870001799136, "count": 8, "is_parallel": true, "self": 0.0012439870001799136 } } } } } } }, "UnityEnvironment.step": { "total": 1475.7789702628997, "count": 64135, "is_parallel": true, "self": 32.66858775274795, "children": { "UnityEnvironment._generate_step_input": { "total": 23.828478418076884, "count": 64135, "is_parallel": true, "self": 23.828478418076884 }, "communicator.exchange": { "total": 1322.8868224250855, "count": 64135, "is_parallel": true, "self": 1322.8868224250855 }, "steps_from_proto": { "total": 96.39508166698943, "count": 64135, "is_parallel": true, "self": 20.856376408030428, "children": { "_process_rank_one_or_two_observation": { "total": 75.538705258959, "count": 513080, "is_parallel": true, "self": 75.538705258959 } } } } } } } } } } }, "trainer_advance": { "total": 651.5649583709669, "count": 64136, "self": 2.951220375955927, "children": { "process_trajectory": { "total": 123.30545854101001, "count": 64136, "self": 123.0495682210103, "children": { "RLTrainer._checkpoint": { "total": 0.25589031999970757, "count": 2, "self": 0.25589031999970757 } } }, "_update_policy": { "total": 525.308279454001, "count": 453, "self": 335.06011000804165, "children": { "TorchPPOOptimizer.update": { "total": 190.24816944595932, "count": 22782, "self": 190.24816944595932 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.09944008599995868, "count": 1, "self": 0.003862168000523525, "children": { "RLTrainer._checkpoint": { "total": 0.09557791799943516, "count": 1, "self": 0.09557791799943516 } } } } } } }