{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5742052793502808, "min": 0.5682278275489807, "max": 1.4005942344665527, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17474.21484375, "min": 17128.66015625, "max": 42488.42578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5763970613479614, "min": -0.08879601955413818, "max": 0.5763970613479614, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.23838806152344, "min": -21.488636016845703, "max": 160.23838806152344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004741943906992674, "min": -0.00580231286585331, "max": 0.22917023301124573, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3182604312896729, "min": -1.4853920936584473, "max": 55.23002624511719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06787203408114766, "min": 0.0647743030557463, "max": 0.07255231813770988, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9502084771360672, "min": 0.5078662269639691, "max": 1.0677849865945366, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013498938319528296, "min": 0.0006372133692594429, "max": 0.015566573493505981, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18898513647339615, "min": 0.008283773800372757, "max": 0.2238802523383592, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.260183294257141e-06, "min": 7.260183294257141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010164256611959997, "min": 0.00010164256611959997, "max": 0.0036329458890180994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242002857142858, "min": 0.10242002857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338804, "min": 1.3886848, "max": 2.6109819, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025176085428571423, "min": 0.00025176085428571423, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035246519599999994, "min": 0.0035246519599999994, "max": 0.12111709181, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008201077580451965, "min": 0.008201077580451965, "max": 0.4244433343410492, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11481508612632751, "min": 0.11481508612632751, "max": 2.9711034297943115, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.2261904761905, "min": 329.2261904761905, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27655.0, "min": 15984.0, "max": 33186.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6253505754996749, "min": -1.0000000521540642, "max": 1.6253505754996749, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.15479891747236, "min": -29.216601714491844, "max": 138.15479891747236, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6253505754996749, "min": -1.0000000521540642, "max": 1.6253505754996749, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.15479891747236, "min": -29.216601714491844, "max": 138.15479891747236, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028295113439397775, "min": 0.028295113439397775, "max": 8.74701570160687, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.405084642348811, "min": 2.405084642348811, "max": 139.95225122570992, "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": "1692195982", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramidsv1 --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": "1692198223" }, "total": 2240.465773029, "count": 1, "self": 0.4761246600000959, "children": { "run_training.setup": { "total": 0.0458647769999061, "count": 1, "self": 0.0458647769999061 }, "TrainerController.start_learning": { "total": 2239.943783592, "count": 1, "self": 1.5192010500154538, "children": { "TrainerController._reset_env": { "total": 4.082494433999955, "count": 1, "self": 4.082494433999955 }, "TrainerController.advance": { "total": 2234.245993317985, "count": 63664, "self": 1.48061414389349, "children": { "env_step": { "total": 1554.191480662033, "count": 63664, "self": 1440.3550349620873, "children": { "SubprocessEnvManager._take_step": { "total": 112.93128359597381, "count": 63664, "self": 4.878259548967208, "children": { "TorchPolicy.evaluate": { "total": 108.0530240470066, "count": 62559, "self": 108.0530240470066 } } }, "workers": { "total": 0.9051621039718611, "count": 63664, "self": 0.0, "children": { "worker_root": { "total": 2234.87381689997, "count": 63664, "is_parallel": true, "self": 913.4047483199163, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017323689999102498, "count": 1, "is_parallel": true, "self": 0.0005411139995885605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011912550003216893, "count": 8, "is_parallel": true, "self": 0.0011912550003216893 } } }, "UnityEnvironment.step": { "total": 0.04788857400012603, "count": 1, "is_parallel": true, "self": 0.0005423420002443891, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004810460000044259, "count": 1, "is_parallel": true, "self": 0.0004810460000044259 }, "communicator.exchange": { "total": 0.044962898999983736, "count": 1, "is_parallel": true, "self": 0.044962898999983736 }, "steps_from_proto": { "total": 0.0019022869998934766, "count": 1, "is_parallel": true, "self": 0.0003916939997452573, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015105930001482193, "count": 8, "is_parallel": true, "self": 0.0015105930001482193 } } } } } } }, "UnityEnvironment.step": { "total": 1321.4690685800535, "count": 63663, "is_parallel": true, "self": 34.97529759805957, "children": { "UnityEnvironment._generate_step_input": { "total": 23.5576400079417, "count": 63663, "is_parallel": true, "self": 23.5576400079417 }, "communicator.exchange": { "total": 1155.082868845029, "count": 63663, "is_parallel": true, "self": 1155.082868845029 }, "steps_from_proto": { "total": 107.85326212902328, "count": 63663, "is_parallel": true, "self": 21.299901460096635, "children": { "_process_rank_one_or_two_observation": { "total": 86.55336066892664, "count": 509304, "is_parallel": true, "self": 86.55336066892664 } } } } } } } } } } }, "trainer_advance": { "total": 678.5738985120581, "count": 63664, "self": 2.8233228510605386, "children": { "process_trajectory": { "total": 114.06251434199908, "count": 63664, "self": 113.84562388599875, "children": { "RLTrainer._checkpoint": { "total": 0.2168904560003284, "count": 2, "self": 0.2168904560003284 } } }, "_update_policy": { "total": 561.6880613189985, "count": 451, "self": 368.11544143899437, "children": { "TorchPPOOptimizer.update": { "total": 193.57261988000414, "count": 22758, "self": 193.57261988000414 } } } } } } }, "trainer_threads": { "total": 8.669999260746408e-07, "count": 1, "self": 8.669999260746408e-07 }, "TrainerController._save_models": { "total": 0.0960939229998985, "count": 1, "self": 0.0013911209998695995, "children": { "RLTrainer._checkpoint": { "total": 0.0947028020000289, "count": 1, "self": 0.0947028020000289 } } } } } } }