{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47647625207901, "min": 0.4703928530216217, "max": 1.4778077602386475, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14126.568359375, "min": 14126.568359375, "max": 44830.77734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09673085063695908, "min": -0.10418783873319626, "max": 0.1480855792760849, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 23.98925018310547, "min": -25.005081176757812, "max": 37.31756591796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07545746117830276, "min": -0.02154764160513878, "max": 0.45023784041404724, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.713449478149414, "min": -5.386910438537598, "max": 106.70636749267578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06826556749910596, "min": 0.06405026209089987, "max": 0.07485475299785475, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9557179449874834, "min": 0.4865711059945839, "max": 1.053522759700404, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007872157828629595, "min": 8.705279137967656e-05, "max": 0.008552701834127046, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11021020960081433, "min": 0.0011316862879357952, "max": 0.11973782567777864, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.302204708821429e-06, "min": 7.302204708821429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010223086592350001, "min": 0.00010223086592350001, "max": 0.0035079686306772, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024340357142857, "min": 0.1024340357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340765, "min": 1.327104, "max": 2.5693228, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002531601678571429, "min": 0.0002531601678571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035442423500000003, "min": 0.0035442423500000003, "max": 0.11695534772000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013297267258167267, "min": 0.013297267258167267, "max": 0.40652650594711304, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18616174161434174, "min": 0.18616174161434174, "max": 2.8456854820251465, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 754.7631578947369, "min": 679.2727272727273, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28681.0, "min": 15984.0, "max": 32839.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.21304611536936882, "min": -1.0000000521540642, "max": 0.5837394969407902, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 8.308798499405384, "min": -32.000001668930054, "max": 25.10079836845398, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.21304611536936882, "min": -1.0000000521540642, "max": 0.5837394969407902, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 8.308798499405384, "min": -32.000001668930054, "max": 25.10079836845398, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10342532117964509, "min": 0.09636587493370699, "max": 8.65759839117527, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.033587526006158, "min": 4.033587526006158, "max": 138.52157425880432, "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": "1682523393", "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": "1682525469" }, "total": 2075.862905726, "count": 1, "self": 0.4742682800001603, "children": { "run_training.setup": { "total": 0.10588852999990195, "count": 1, "self": 0.10588852999990195 }, "TrainerController.start_learning": { "total": 2075.282748916, "count": 1, "self": 1.2992539859960743, "children": { "TrainerController._reset_env": { "total": 3.732118653000043, "count": 1, "self": 3.732118653000043 }, "TrainerController.advance": { "total": 2070.160367733004, "count": 63300, "self": 1.3539181910464322, "children": { "env_step": { "total": 1442.5740042350171, "count": 63300, "self": 1339.00506144304, "children": { "SubprocessEnvManager._take_step": { "total": 102.72036689304673, "count": 63300, "self": 4.601454368100349, "children": { "TorchPolicy.evaluate": { "total": 98.11891252494638, "count": 62560, "self": 98.11891252494638 } } }, "workers": { "total": 0.8485758989304486, "count": 63300, "self": 0.0, "children": { "worker_root": { "total": 2070.4980956379627, "count": 63300, "is_parallel": true, "self": 838.990533957943, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001805150000109279, "count": 1, "is_parallel": true, "self": 0.0005683240001417289, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012368259999675502, "count": 8, "is_parallel": true, "self": 0.0012368259999675502 } } }, "UnityEnvironment.step": { "total": 0.0507011050001438, "count": 1, "is_parallel": true, "self": 0.0005967640001927066, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005316069998571038, "count": 1, "is_parallel": true, "self": 0.0005316069998571038 }, "communicator.exchange": { "total": 0.047836638000035236, "count": 1, "is_parallel": true, "self": 0.047836638000035236 }, "steps_from_proto": { "total": 0.001736096000058751, "count": 1, "is_parallel": true, "self": 0.00037544099996011937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013606550000986317, "count": 8, "is_parallel": true, "self": 0.0013606550000986317 } } } } } } }, "UnityEnvironment.step": { "total": 1231.5075616800198, "count": 63299, "is_parallel": true, "self": 31.457113281018337, "children": { "UnityEnvironment._generate_step_input": { "total": 21.9380766470058, "count": 63299, "is_parallel": true, "self": 21.9380766470058 }, "communicator.exchange": { "total": 1088.0371952179764, "count": 63299, "is_parallel": true, "self": 1088.0371952179764 }, "steps_from_proto": { "total": 90.07517653401919, "count": 63299, "is_parallel": true, "self": 18.923784181030896, "children": { "_process_rank_one_or_two_observation": { "total": 71.1513923529883, "count": 506392, "is_parallel": true, "self": 71.1513923529883 } } } } } } } } } } }, "trainer_advance": { "total": 626.2324453069402, "count": 63300, "self": 2.383568186965931, "children": { "process_trajectory": { "total": 103.3419721709729, "count": 63300, "self": 103.08993013897316, "children": { "RLTrainer._checkpoint": { "total": 0.2520420319997356, "count": 2, "self": 0.2520420319997356 } } }, "_update_policy": { "total": 520.5069049490014, "count": 435, "self": 337.6159242629742, "children": { "TorchPPOOptimizer.update": { "total": 182.8909806860272, "count": 22791, "self": 182.8909806860272 } } } } } } }, "trainer_threads": { "total": 1.0170001587539446e-06, "count": 1, "self": 1.0170001587539446e-06 }, "TrainerController._save_models": { "total": 0.09100752699987424, "count": 1, "self": 0.0015558849995613855, "children": { "RLTrainer._checkpoint": { "total": 0.08945164200031286, "count": 1, "self": 0.08945164200031286 } } } } } } }