{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23803405463695526, "min": 0.18448559939861298, "max": 1.4448875188827515, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7083.8935546875, "min": 5478.484375, "max": 43832.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19662602245807648, "min": -0.140786811709404, "max": 0.2362356036901474, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 50.1396369934082, "min": -33.78883361816406, "max": 60.00384521484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.13691918551921844, "min": 0.07717489451169968, "max": 0.44547340273857117, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 34.914390563964844, "min": 19.52524757385254, "max": 105.57719421386719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06957270760419003, "min": 0.06475037341082189, "max": 0.07377696674675925, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9740179064586604, "min": 0.5164387672273147, "max": 1.0742604772807967, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008933475679787946, "min": 0.0005500481453716315, "max": 0.010300285888284117, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12506865951703125, "min": 0.004950433308344684, "max": 0.14420400243597764, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.67896172609286e-06, "min": 7.67896172609286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010750546416530005, "min": 0.00010750546416530005, "max": 0.003511298329567299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255962142857143, "min": 0.10255962142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358347, "min": 1.3886848, "max": 2.5704327000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026570618071428587, "min": 0.00026570618071428587, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003719886530000002, "min": 0.003719886530000002, "max": 0.11706622672999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.16269998252391815, "min": 0.13679160177707672, "max": 0.5634230375289917, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.2777998447418213, "min": 1.694376826286316, "max": 3.9439613819122314, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 620.8846153846154, "min": 516.3061224489796, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32286.0, "min": 15984.0, "max": 32707.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6170527918158837, "min": -1.0000000521540642, "max": 1.0352999727862577, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 32.70379796624184, "min": -31.998401656746864, "max": 49.69439869374037, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6170527918158837, "min": -1.0000000521540642, "max": 1.0352999727862577, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 32.70379796624184, "min": -31.998401656746864, "max": 49.69439869374037, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 1.0395195446930439, "min": 0.7975240715507729, "max": 11.12066927459091, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 55.09453586873133, "min": 38.281155434437096, "max": 177.93070839345455, "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": "1677986107", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677988187" }, "total": 2079.3772691039994, "count": 1, "self": 0.7998623399994358, "children": { "run_training.setup": { "total": 0.10438413200017749, "count": 1, "self": 0.10438413200017749 }, "TrainerController.start_learning": { "total": 2078.473022632, "count": 1, "self": 1.3356444400669716, "children": { "TrainerController._reset_env": { "total": 6.979068892999749, "count": 1, "self": 6.979068892999749 }, "TrainerController.advance": { "total": 2070.027830915934, "count": 63500, "self": 1.3782036670081652, "children": { "env_step": { "total": 1329.6685975119972, "count": 63500, "self": 1217.436132929868, "children": { "SubprocessEnvManager._take_step": { "total": 111.42988129617288, "count": 63500, "self": 4.584819240154957, "children": { "TorchPolicy.evaluate": { "total": 106.84506205601792, "count": 62558, "self": 36.216157503966315, "children": { "TorchPolicy.sample_actions": { "total": 70.62890455205161, "count": 62558, "self": 70.62890455205161 } } } } }, "workers": { "total": 0.8025832859561888, "count": 63500, "self": 0.0, "children": { "worker_root": { "total": 2074.127618057035, "count": 63500, "is_parallel": true, "self": 966.9202418470518, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019386949998079217, "count": 1, "is_parallel": true, "self": 0.0007748609991722333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011638340006356884, "count": 8, "is_parallel": true, "self": 0.0011638340006356884 } } }, "UnityEnvironment.step": { "total": 0.04466403700007504, "count": 1, "is_parallel": true, "self": 0.000529655999798706, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043978000030620024, "count": 1, "is_parallel": true, "self": 0.00043978000030620024 }, "communicator.exchange": { "total": 0.04212991400027022, "count": 1, "is_parallel": true, "self": 0.04212991400027022 }, "steps_from_proto": { "total": 0.0015646869996999158, "count": 1, "is_parallel": true, "self": 0.00039103300014176057, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011736539995581552, "count": 8, "is_parallel": true, "self": 0.0011736539995581552 } } } } } } }, "UnityEnvironment.step": { "total": 1107.207376209983, "count": 63499, "is_parallel": true, "self": 30.860618582041297, "children": { "UnityEnvironment._generate_step_input": { "total": 22.637759334103066, "count": 63499, "is_parallel": true, "self": 22.637759334103066 }, "communicator.exchange": { "total": 963.7782745869094, "count": 63499, "is_parallel": true, "self": 963.7782745869094 }, "steps_from_proto": { "total": 89.93072370692926, "count": 63499, "is_parallel": true, "self": 21.09044539376646, "children": { "_process_rank_one_or_two_observation": { "total": 68.8402783131628, "count": 507992, "is_parallel": true, "self": 68.8402783131628 } } } } } } } } } } }, "trainer_advance": { "total": 738.9810297369286, "count": 63500, "self": 2.574450564827657, "children": { "process_trajectory": { "total": 159.17634014709483, "count": 63500, "self": 158.94476421709533, "children": { "RLTrainer._checkpoint": { "total": 0.23157592999950793, "count": 2, "self": 0.23157592999950793 } } }, "_update_policy": { "total": 577.2302390250061, "count": 449, "self": 223.46443134702804, "children": { "TorchPPOOptimizer.update": { "total": 353.76580767797805, "count": 22809, "self": 353.76580767797805 } } } } } } }, "trainer_threads": { "total": 1.2009995771222748e-06, "count": 1, "self": 1.2009995771222748e-06 }, "TrainerController._save_models": { "total": 0.1304771819995949, "count": 1, "self": 0.0019837319996440783, "children": { "RLTrainer._checkpoint": { "total": 0.12849344999995083, "count": 1, "self": 0.12849344999995083 } } } } } } }