{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.49181291460990906, "min": 0.49181291460990906, "max": 1.4455914497375488, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14667.828125, "min": 14667.828125, "max": 43853.4609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2894212603569031, "min": -0.10006245970726013, "max": 0.2894212603569031, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 74.09184265136719, "min": -24.115053176879883, "max": 74.09184265136719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05867832899093628, "min": -0.01819816417992115, "max": 0.26599156856536865, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.021652221679688, "min": -4.604135513305664, "max": 63.837974548339844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07083265967281496, "min": 0.06657487815878607, "max": 0.07560739415100516, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9916572354194095, "min": 0.4706596275676114, "max": 1.0968478921767753, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011370804733952593, "min": 8.41548360268593e-05, "max": 0.011370804733952593, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1591912662753363, "min": 0.0010940128683491709, "max": 0.1591912662753363, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.42563323910714e-06, "min": 7.42563323910714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010395886534749997, "min": 0.00010395886534749997, "max": 0.0032240149253283997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247517857142859, "min": 0.10247517857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346525, "min": 1.3691136000000002, "max": 2.3463482, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025727033928571425, "min": 0.00025727033928571425, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036017847499999994, "min": 0.0036017847499999994, "max": 0.10747969283999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011043327860534191, "min": 0.011043327860534191, "max": 0.35828956961631775, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15460659563541412, "min": 0.15460659563541412, "max": 2.5080270767211914, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 557.2452830188679, "min": 557.2452830188679, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29534.0, "min": 15984.0, "max": 32374.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2162641160330683, "min": -1.0000000521540642, "max": 1.2162641160330683, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.46199814975262, "min": -32.000001668930054, "max": 64.46199814975262, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2162641160330683, "min": -1.0000000521540642, "max": 1.2162641160330683, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.46199814975262, "min": -32.000001668930054, "max": 64.46199814975262, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06446990762608794, "min": 0.06446990762608794, "max": 7.403607062995434, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4169051041826606, "min": 3.3402350553078577, "max": 118.45771300792694, "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": "1683598012", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683600121" }, "total": 2108.776401729, "count": 1, "self": 0.4859136449995276, "children": { "run_training.setup": { "total": 0.03998192799997469, "count": 1, "self": 0.03998192799997469 }, "TrainerController.start_learning": { "total": 2108.2505061560005, "count": 1, "self": 1.4414895709555822, "children": { "TrainerController._reset_env": { "total": 3.9781886590000113, "count": 1, "self": 3.9781886590000113 }, "TrainerController.advance": { "total": 2102.724371694045, "count": 63241, "self": 1.4430576790682608, "children": { "env_step": { "total": 1438.3042968650266, "count": 63241, "self": 1325.6335420400515, "children": { "SubprocessEnvManager._take_step": { "total": 111.8315255649901, "count": 63241, "self": 4.845015252977419, "children": { "TorchPolicy.evaluate": { "total": 106.98651031201268, "count": 62569, "self": 106.98651031201268 } } }, "workers": { "total": 0.8392292599851316, "count": 63241, "self": 0.0, "children": { "worker_root": { "total": 2103.2736115829475, "count": 63241, "is_parallel": true, "self": 891.6589402639461, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015706850000469785, "count": 1, "is_parallel": true, "self": 0.00040512700013550784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011655579999114707, "count": 8, "is_parallel": true, "self": 0.0011655579999114707 } } }, "UnityEnvironment.step": { "total": 0.04885625099996105, "count": 1, "is_parallel": true, "self": 0.0005151949999344652, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000498240999945665, "count": 1, "is_parallel": true, "self": 0.000498240999945665 }, "communicator.exchange": { "total": 0.04602067500002249, "count": 1, "is_parallel": true, "self": 0.04602067500002249 }, "steps_from_proto": { "total": 0.0018221400000584254, "count": 1, "is_parallel": true, "self": 0.00034981499982222886, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014723250002361965, "count": 8, "is_parallel": true, "self": 0.0014723250002361965 } } } } } } }, "UnityEnvironment.step": { "total": 1211.6146713190014, "count": 63240, "is_parallel": true, "self": 32.71901322313056, "children": { "UnityEnvironment._generate_step_input": { "total": 23.56339442394642, "count": 63240, "is_parallel": true, "self": 23.56339442394642 }, "communicator.exchange": { "total": 1055.3729081719525, "count": 63240, "is_parallel": true, "self": 1055.3729081719525 }, "steps_from_proto": { "total": 99.95935549997193, "count": 63240, "is_parallel": true, "self": 20.17279917293581, "children": { "_process_rank_one_or_two_observation": { "total": 79.78655632703612, "count": 505920, "is_parallel": true, "self": 79.78655632703612 } } } } } } } } } } }, "trainer_advance": { "total": 662.9770171499504, "count": 63241, "self": 2.4872599709621, "children": { "process_trajectory": { "total": 108.86378961198898, "count": 63241, "self": 108.6480393569891, "children": { "RLTrainer._checkpoint": { "total": 0.21575025499987532, "count": 2, "self": 0.21575025499987532 } } }, "_update_policy": { "total": 551.6259675669993, "count": 434, "self": 354.48789628997054, "children": { "TorchPPOOptimizer.update": { "total": 197.13807127702876, "count": 22944, "self": 197.13807127702876 } } } } } } }, "trainer_threads": { "total": 1.0919998203462455e-06, "count": 1, "self": 1.0919998203462455e-06 }, "TrainerController._save_models": { "total": 0.10645513999998002, "count": 1, "self": 0.002088767000259395, "children": { "RLTrainer._checkpoint": { "total": 0.10436637299972062, "count": 1, "self": 0.10436637299972062 } } } } } } }