{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.537469208240509, "min": 0.537469208240509, "max": 1.4602720737457275, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16081.078125, "min": 16081.078125, "max": 44298.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5477339625358582, "min": -0.1155085414648056, "max": 0.5477339625358582, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 152.81777954101562, "min": -27.953067779541016, "max": 152.81777954101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007286582607775927, "min": -0.03917496278882027, "max": 0.2708534896373749, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.032956600189209, "min": -10.381364822387695, "max": 65.54654693603516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06870663790600484, "min": 0.06585085634448688, "max": 0.07362447643685692, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9618929306840678, "min": 0.511078340184725, "max": 1.0547077266268852, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01502501104481607, "min": 0.0006209250926686348, "max": 0.01502501104481607, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21035015462742498, "min": 0.008692951297360888, "max": 0.21035015462742498, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.384747538450001e-06, "min": 7.384747538450001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010338646553830001, "min": 0.00010338646553830001, "max": 0.0036332071889310005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246155000000001, "min": 0.10246155000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344617000000002, "min": 1.3886848, "max": 2.6110689999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025590884500000015, "min": 0.00025590884500000015, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035827238300000022, "min": 0.0035827238300000022, "max": 0.1211257931, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011887529864907265, "min": 0.01175712700933218, "max": 0.40382641553878784, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.166425421833992, "min": 0.16459977626800537, "max": 2.82678484916687, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 343.22222222222223, "min": 343.22222222222223, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30890.0, "min": 15984.0, "max": 32989.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5355888722671402, "min": -1.0000000521540642, "max": 1.5395487013917704, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.20299850404263, "min": -28.197001732885838, "max": 138.20299850404263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5355888722671402, "min": -1.0000000521540642, "max": 1.5395487013917704, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.20299850404263, "min": -28.197001732885838, "max": 138.20299850404263, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04327827774638233, "min": 0.04327827774638233, "max": 7.453175722621381, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.895044997174409, "min": 3.4759267813933548, "max": 119.2508115619421, "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": "1698956229", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698957682" }, "total": 1453.056970418, "count": 1, "self": 0.371980210999709, "children": { "run_training.setup": { "total": 0.04032402200004981, "count": 1, "self": 0.04032402200004981 }, "TrainerController.start_learning": { "total": 1452.6446661850002, "count": 1, "self": 1.0569437970113995, "children": { "TrainerController._reset_env": { "total": 3.385779236000076, "count": 1, "self": 3.385779236000076 }, "TrainerController.advance": { "total": 1448.1311863409892, "count": 63634, "self": 1.0902291411184706, "children": { "env_step": { "total": 935.0803603578981, "count": 63634, "self": 829.4690710919295, "children": { "SubprocessEnvManager._take_step": { "total": 104.96687454795483, "count": 63634, "self": 3.8377414529923044, "children": { "TorchPolicy.evaluate": { "total": 101.12913309496253, "count": 62561, "self": 101.12913309496253 } } }, "workers": { "total": 0.6444147180137634, "count": 63634, "self": 0.0, "children": { "worker_root": { "total": 1450.8360712980016, "count": 63634, "is_parallel": true, "self": 702.0642350619721, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018041579999135138, "count": 1, "is_parallel": true, "self": 0.0005561049997595546, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012480530001539591, "count": 8, "is_parallel": true, "self": 0.0012480530001539591 } } }, "UnityEnvironment.step": { "total": 0.03364381200003663, "count": 1, "is_parallel": true, "self": 0.00033310100013750343, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002834050000046773, "count": 1, "is_parallel": true, "self": 0.0002834050000046773 }, "communicator.exchange": { "total": 0.03195716999994147, "count": 1, "is_parallel": true, "self": 0.03195716999994147 }, "steps_from_proto": { "total": 0.0010701359999529814, "count": 1, "is_parallel": true, "self": 0.0002338089998374926, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008363270001154888, "count": 8, "is_parallel": true, "self": 0.0008363270001154888 } } } } } } }, "UnityEnvironment.step": { "total": 748.7718362360295, "count": 63633, "is_parallel": true, "self": 19.895991991093297, "children": { "UnityEnvironment._generate_step_input": { "total": 13.851949299016155, "count": 63633, "is_parallel": true, "self": 13.851949299016155 }, "communicator.exchange": { "total": 658.4641740669387, "count": 63633, "is_parallel": true, "self": 658.4641740669387 }, "steps_from_proto": { "total": 56.55972087898135, "count": 63633, "is_parallel": true, "self": 11.945073903034427, "children": { "_process_rank_one_or_two_observation": { "total": 44.614646975946926, "count": 509064, "is_parallel": true, "self": 44.614646975946926 } } } } } } } } } } }, "trainer_advance": { "total": 511.9605968419727, "count": 63634, "self": 2.0591762999576986, "children": { "process_trajectory": { "total": 97.112013756014, "count": 63634, "self": 96.94710044301405, "children": { "RLTrainer._checkpoint": { "total": 0.16491331299994272, "count": 2, "self": 0.16491331299994272 } } }, "_update_policy": { "total": 412.789406786001, "count": 453, "self": 239.33156542198867, "children": { "TorchPPOOptimizer.update": { "total": 173.45784136401232, "count": 22809, "self": 173.45784136401232 } } } } } } }, "trainer_threads": { "total": 8.869997145666275e-07, "count": 1, "self": 8.869997145666275e-07 }, "TrainerController._save_models": { "total": 0.07075592399996822, "count": 1, "self": 0.0013630660000671924, "children": { "RLTrainer._checkpoint": { "total": 0.06939285799990103, "count": 1, "self": 0.06939285799990103 } } } } } } }