{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42661282420158386, "min": 0.42661282420158386, "max": 1.4351681470870972, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12921.2490234375, "min": 12921.2490234375, "max": 43537.26171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4852186441421509, "min": -0.13499201834201813, "max": 0.5720705986022949, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.46469116210938, "min": -32.533077239990234, "max": 155.0311279296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025193121284246445, "min": 0.012406974099576473, "max": 0.5613970756530762, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.877722263336182, "min": 3.3622899055480957, "max": 141.47206115722656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06708143480050023, "min": 0.0627065204759422, "max": 0.07369771965192316, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9391400872070033, "min": 0.5158840375634621, "max": 1.073817646136626, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01377473336088726, "min": 0.000786386372923066, "max": 0.049710626967020756, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19284626705242164, "min": 0.008650250102153726, "max": 0.7456594045053113, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.530054632871431e-06, "min": 7.530054632871431e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010542076486020003, "min": 0.00010542076486020003, "max": 0.0035074394308536004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250998571428574, "min": 0.10250998571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351398000000004, "min": 1.3886848, "max": 2.5724618999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000260747572857143, "min": 0.000260747572857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003650466020000002, "min": 0.003650466020000002, "max": 0.11693772536, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010629934258759022, "min": 0.010629934258759022, "max": 0.3827984929084778, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14881907403469086, "min": 0.14881907403469086, "max": 2.6795895099639893, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 391.05263157894734, "min": 315.5698924731183, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29720.0, "min": 15984.0, "max": 33136.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.446722647746404, "min": -1.0000000521540642, "max": 1.6414021140241877, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 108.5041985809803, "min": -29.913001619279385, "max": 154.29179871827364, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.446722647746404, "min": -1.0000000521540642, "max": 1.6414021140241877, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 108.5041985809803, "min": -29.913001619279385, "max": 154.29179871827364, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04375640034675598, "min": 0.036383640326830766, "max": 6.595312531106174, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2817300260066986, "min": 3.185614061949309, "max": 105.52500049769878, "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": "1679214608", "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": "1679216728" }, "total": 2119.9186658400004, "count": 1, "self": 0.4885479950003173, "children": { "run_training.setup": { "total": 0.1019306250000227, "count": 1, "self": 0.1019306250000227 }, "TrainerController.start_learning": { "total": 2119.32818722, "count": 1, "self": 1.5074590329090825, "children": { "TrainerController._reset_env": { "total": 6.080862118999903, "count": 1, "self": 6.080862118999903 }, "TrainerController.advance": { "total": 2111.6495691970904, "count": 63829, "self": 1.4765579171130412, "children": { "env_step": { "total": 1500.8434629269727, "count": 63829, "self": 1391.2299272500886, "children": { "SubprocessEnvManager._take_step": { "total": 108.72991550888992, "count": 63829, "self": 4.767345487919101, "children": { "TorchPolicy.evaluate": { "total": 103.96257002097082, "count": 62557, "self": 103.96257002097082 } } }, "workers": { "total": 0.8836201679941951, "count": 63829, "self": 0.0, "children": { "worker_root": { "total": 2114.752070794908, "count": 63829, "is_parallel": true, "self": 842.5170535479065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002816915000039444, "count": 1, "is_parallel": true, "self": 0.0006963209998502862, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021205940001891577, "count": 8, "is_parallel": true, "self": 0.0021205940001891577 } } }, "UnityEnvironment.step": { "total": 0.05856046500002776, "count": 1, "is_parallel": true, "self": 0.0006021429999236716, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005100970001876703, "count": 1, "is_parallel": true, "self": 0.0005100970001876703 }, "communicator.exchange": { "total": 0.05560618199979217, "count": 1, "is_parallel": true, "self": 0.05560618199979217 }, "steps_from_proto": { "total": 0.0018420430001242494, "count": 1, "is_parallel": true, "self": 0.0004097669993825548, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014322760007416946, "count": 8, "is_parallel": true, "self": 0.0014322760007416946 } } } } } } }, "UnityEnvironment.step": { "total": 1272.2350172470015, "count": 63828, "is_parallel": true, "self": 30.676713851984005, "children": { "UnityEnvironment._generate_step_input": { "total": 22.37188011700937, "count": 63828, "is_parallel": true, "self": 22.37188011700937 }, "communicator.exchange": { "total": 1128.8535302699906, "count": 63828, "is_parallel": true, "self": 1128.8535302699906 }, "steps_from_proto": { "total": 90.33289300801744, "count": 63828, "is_parallel": true, "self": 19.5236570719494, "children": { "_process_rank_one_or_two_observation": { "total": 70.80923593606803, "count": 510624, "is_parallel": true, "self": 70.80923593606803 } } } } } } } } } } }, "trainer_advance": { "total": 609.3295483530046, "count": 63829, "self": 2.795314255037738, "children": { "process_trajectory": { "total": 115.2220620709586, "count": 63829, "self": 114.9575418249583, "children": { "RLTrainer._checkpoint": { "total": 0.264520246000302, "count": 2, "self": 0.264520246000302 } } }, "_update_policy": { "total": 491.3121720270083, "count": 450, "self": 312.82163911499947, "children": { "TorchPPOOptimizer.update": { "total": 178.4905329120088, "count": 22821, "self": 178.4905329120088 } } } } } } }, "trainer_threads": { "total": 9.229997885995544e-07, "count": 1, "self": 9.229997885995544e-07 }, "TrainerController._save_models": { "total": 0.0902959480008576, "count": 1, "self": 0.0018645580003067153, "children": { "RLTrainer._checkpoint": { "total": 0.08843139000055089, "count": 1, "self": 0.08843139000055089 } } } } } } }