{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7573220729827881, "min": 0.6773127317428589, "max": 1.4825916290283203, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22731.779296875, "min": 20492.7734375, "max": 44975.8984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27447617053985596, "min": -0.10133589804172516, "max": 0.27447617053985596, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 70.26589965820312, "min": -24.421951293945312, "max": 70.26589965820312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.40304917097091675, "min": -0.40304917097091675, "max": 0.24887628853321075, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -103.18058776855469, "min": -103.18058776855469, "max": 59.730308532714844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0671766853831964, "min": 0.06604293783010096, "max": 0.07415929620214609, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9404735953647497, "min": 0.47799978395736636, "max": 1.0644891222182196, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.04909432912820132, "min": 6.204955642325722e-05, "max": 0.04909432912820132, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.6873206077948184, "min": 0.000868693789925601, "max": 0.6873206077948184, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.292497569200001e-06, "min": 7.292497569200001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010209496596880001, "min": 0.00010209496596880001, "max": 0.003507092030969399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243080000000002, "min": 0.10243080000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340312000000002, "min": 1.3691136000000002, "max": 2.5690305999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002528369200000001, "min": 0.0002528369200000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035397168800000013, "min": 0.0035397168800000013, "max": 0.11692615693999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010131115093827248, "min": 0.010131115093827248, "max": 0.3427746295928955, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14183561503887177, "min": 0.14183561503887177, "max": 2.3994224071502686, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 549.4423076923077, "min": 549.4423076923077, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28571.0, "min": 15984.0, "max": 34211.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0645735567470767, "min": -1.0000000521540642, "max": 1.0645735567470767, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 56.42239850759506, "min": -32.000001668930054, "max": 56.42239850759506, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0645735567470767, "min": -1.0000000521540642, "max": 1.0645735567470767, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 56.42239850759506, "min": -32.000001668930054, "max": 56.42239850759506, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05905671373425921, "min": 0.05905671373425921, "max": 6.541038376279175, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1300058279157383, "min": 3.0857588361541275, "max": 104.6566140204668, "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": "1704381796", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704384154" }, "total": 2357.4887353190006, "count": 1, "self": 0.6790395720013294, "children": { "run_training.setup": { "total": 0.05330390799963425, "count": 1, "self": 0.05330390799963425 }, "TrainerController.start_learning": { "total": 2356.7563918389997, "count": 1, "self": 1.7697440339989043, "children": { "TrainerController._reset_env": { "total": 2.3886428740001975, "count": 1, "self": 2.3886428740001975 }, "TrainerController.advance": { "total": 2352.507404685001, "count": 63338, "self": 1.890619765125848, "children": { "env_step": { "total": 1647.3705918679962, "count": 63338, "self": 1491.061822430985, "children": { "SubprocessEnvManager._take_step": { "total": 155.20086220300072, "count": 63338, "self": 5.760897397910867, "children": { "TorchPolicy.evaluate": { "total": 149.43996480508986, "count": 62570, "self": 149.43996480508986 } } }, "workers": { "total": 1.1079072340103266, "count": 63338, "self": 0.0, "children": { "worker_root": { "total": 2350.655095981099, "count": 63338, "is_parallel": true, "self": 1000.306323443262, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017355549998683273, "count": 1, "is_parallel": true, "self": 0.0005494870001712115, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011860679996971157, "count": 8, "is_parallel": true, "self": 0.0011860679996971157 } } }, "UnityEnvironment.step": { "total": 0.09755287600000884, "count": 1, "is_parallel": true, "self": 0.0006027109998285596, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046307799993883236, "count": 1, "is_parallel": true, "self": 0.00046307799993883236 }, "communicator.exchange": { "total": 0.09483212300028754, "count": 1, "is_parallel": true, "self": 0.09483212300028754 }, "steps_from_proto": { "total": 0.0016549639999539068, "count": 1, "is_parallel": true, "self": 0.00033519900034661987, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013197649996072869, "count": 8, "is_parallel": true, "self": 0.0013197649996072869 } } } } } } }, "UnityEnvironment.step": { "total": 1350.3487725378368, "count": 63337, "is_parallel": true, "self": 40.17028412087711, "children": { "UnityEnvironment._generate_step_input": { "total": 26.799326597972595, "count": 63337, "is_parallel": true, "self": 26.799326597972595 }, "communicator.exchange": { "total": 1174.1521829580151, "count": 63337, "is_parallel": true, "self": 1174.1521829580151 }, "steps_from_proto": { "total": 109.22697886097194, "count": 63337, "is_parallel": true, "self": 23.019208354796774, "children": { "_process_rank_one_or_two_observation": { "total": 86.20777050617517, "count": 506696, "is_parallel": true, "self": 86.20777050617517 } } } } } } } } } } }, "trainer_advance": { "total": 703.2461930518789, "count": 63338, "self": 3.2795123458354283, "children": { "process_trajectory": { "total": 139.63314200204286, "count": 63338, "self": 139.43905495704394, "children": { "RLTrainer._checkpoint": { "total": 0.19408704499892337, "count": 2, "self": 0.19408704499892337 } } }, "_update_policy": { "total": 560.3335387040006, "count": 442, "self": 329.0494961240406, "children": { "TorchPPOOptimizer.update": { "total": 231.28404257996, "count": 22845, "self": 231.28404257996 } } } } } } }, "trainer_threads": { "total": 1.0229996405541897e-06, "count": 1, "self": 1.0229996405541897e-06 }, "TrainerController._save_models": { "total": 0.09059922300002654, "count": 1, "self": 0.0016295360001095105, "children": { "RLTrainer._checkpoint": { "total": 0.08896968699991703, "count": 1, "self": 0.08896968699991703 } } } } } } }