{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3280162811279297, "min": 0.3280162811279297, "max": 1.4801125526428223, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9840.48828125, "min": 9835.88671875, "max": 44900.6953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989966.0, "min": 29952.0, "max": 989966.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989966.0, "min": 29952.0, "max": 989966.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3849741518497467, "min": -0.09375837445259094, "max": 0.4446663558483124, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 103.55804443359375, "min": -22.502010345458984, "max": 119.61524963378906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005030916538089514, "min": 0.004754058551043272, "max": 0.25995418429374695, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3533165454864502, "min": 1.1647443771362305, "max": 62.64896011352539, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06700113532749716, "min": 0.06548365960110412, "max": 0.07372438653437609, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0050170299124574, "min": 0.49897932864915595, "max": 1.0826176931441294, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014164217641100428, "min": 0.000911802304687983, "max": 0.014305029770531249, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21246326461650641, "min": 0.01153153509591268, "max": 0.21246326461650641, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.54353748552e-06, "min": 7.54353748552e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011315306228279999, "min": 0.00011315306228279999, "max": 0.0036325363891545996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251448000000002, "min": 0.10251448000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377172000000003, "min": 1.3886848, "max": 2.6108453999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000261196552, "min": 0.000261196552, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00391794828, "min": 0.00391794828, "max": 0.12110345546000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010143379680812359, "min": 0.010143379680812359, "max": 0.4388962686061859, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1521506905555725, "min": 0.1458950787782669, "max": 3.0722739696502686, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 439.6056338028169, "min": 428.1714285714286, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31212.0, "min": 15984.0, "max": 34008.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3913436380910202, "min": -1.0000000521540642, "max": 1.5146599785557815, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 98.78539830446243, "min": -30.533401682972908, "max": 106.0261984989047, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3913436380910202, "min": -1.0000000521540642, "max": 1.5146599785557815, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 98.78539830446243, "min": -30.533401682972908, "max": 106.0261984989047, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04628501728900157, "min": 0.04628501728900157, "max": 9.750295055098832, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2862362275191117, "min": 3.0904107922979165, "max": 156.0047208815813, "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": "1680844043", "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": "1680846113" }, "total": 2070.003675294, "count": 1, "self": 0.5763190829998166, "children": { "run_training.setup": { "total": 0.18935590999990382, "count": 1, "self": 0.18935590999990382 }, "TrainerController.start_learning": { "total": 2069.2380003010003, "count": 1, "self": 1.4493830100309424, "children": { "TrainerController._reset_env": { "total": 4.293296255999849, "count": 1, "self": 4.293296255999849 }, "TrainerController.advance": { "total": 2063.40393529197, "count": 63580, "self": 1.51849879799056, "children": { "env_step": { "total": 1455.313689405963, "count": 63580, "self": 1348.7929355259325, "children": { "SubprocessEnvManager._take_step": { "total": 105.65817296500882, "count": 63580, "self": 4.730429077050758, "children": { "TorchPolicy.evaluate": { "total": 100.92774388795806, "count": 62554, "self": 100.92774388795806 } } }, "workers": { "total": 0.862580915021681, "count": 63580, "self": 0.0, "children": { "worker_root": { "total": 2064.4183402649433, "count": 63580, "is_parallel": true, "self": 825.3737606279215, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002602690999992774, "count": 1, "is_parallel": true, "self": 0.0007910560007076128, "children": { "_process_rank_one_or_two_observation": { "total": 0.001811634999285161, "count": 8, "is_parallel": true, "self": 0.001811634999285161 } } }, "UnityEnvironment.step": { "total": 0.04835614500007068, "count": 1, "is_parallel": true, "self": 0.0005429429998002888, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005276990000311343, "count": 1, "is_parallel": true, "self": 0.0005276990000311343 }, "communicator.exchange": { "total": 0.045689008999943326, "count": 1, "is_parallel": true, "self": 0.045689008999943326 }, "steps_from_proto": { "total": 0.0015964940002959338, "count": 1, "is_parallel": true, "self": 0.00034151399950133055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012549800007946033, "count": 8, "is_parallel": true, "self": 0.0012549800007946033 } } } } } } }, "UnityEnvironment.step": { "total": 1239.0445796370218, "count": 63579, "is_parallel": true, "self": 32.09596259897444, "children": { "UnityEnvironment._generate_step_input": { "total": 22.576239404064836, "count": 63579, "is_parallel": true, "self": 22.576239404064836 }, "communicator.exchange": { "total": 1091.7282736669727, "count": 63579, "is_parallel": true, "self": 1091.7282736669727 }, "steps_from_proto": { "total": 92.64410396700987, "count": 63579, "is_parallel": true, "self": 19.66795466524627, "children": { "_process_rank_one_or_two_observation": { "total": 72.9761493017636, "count": 508632, "is_parallel": true, "self": 72.9761493017636 } } } } } } } } } } }, "trainer_advance": { "total": 606.5717470880163, "count": 63580, "self": 2.690521165001428, "children": { "process_trajectory": { "total": 102.54988331701225, "count": 63580, "self": 102.34464808401162, "children": { "RLTrainer._checkpoint": { "total": 0.20523523300062152, "count": 2, "self": 0.20523523300062152 } } }, "_update_policy": { "total": 501.33134260600264, "count": 452, "self": 322.28171614801613, "children": { "TorchPPOOptimizer.update": { "total": 179.0496264579865, "count": 22749, "self": 179.0496264579865 } } } } } } }, "trainer_threads": { "total": 1.026999598252587e-06, "count": 1, "self": 1.026999598252587e-06 }, "TrainerController._save_models": { "total": 0.0913847159999932, "count": 1, "self": 0.001456152999708138, "children": { "RLTrainer._checkpoint": { "total": 0.08992856300028507, "count": 1, "self": 0.08992856300028507 } } } } } } }