{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15904517471790314, "min": 0.14119312167167664, "max": 1.4430776834487915, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4786.62353515625, "min": 4231.275390625, "max": 43777.203125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999946.0, "min": 29952.0, "max": 2999946.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999946.0, "min": 29952.0, "max": 2999946.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7888457179069519, "min": -0.09573692083358765, "max": 0.8402525186538696, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 235.07601928710938, "min": -23.07259750366211, "max": 257.95751953125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0013666519662365317, "min": -0.021632174029946327, "max": 0.37051114439964294, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.40726229548454285, "min": -5.925553321838379, "max": 87.81114196777344, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07264763730234423, "min": 0.06444992081313912, "max": 0.07344182118655408, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0170669222328192, "min": 0.4966073289209838, "max": 1.0861939627302848, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015464918590926875, "min": 0.00029515402018361465, "max": 0.01685466549889598, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21650886027297625, "min": 0.0038370022623869906, "max": 0.25281998248343973, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.579520902097621e-06, "min": 1.579520902097621e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2113292629366695e-05, "min": 2.2113292629366695e-05, "max": 0.0039692628769124, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052647380952383, "min": 0.10052647380952383, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073706333333336, "min": 1.3962282666666668, "max": 2.767424733333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.259473357142864e-05, "min": 6.259473357142864e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000876326270000001, "min": 0.000876326270000001, "max": 0.13231645124, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007360729854553938, "min": 0.007156352046877146, "max": 0.4330911338329315, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10305021703243256, "min": 0.10018892586231232, "max": 3.0316379070281982, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 248.22764227642276, "min": 211.21641791044777, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30532.0, "min": 15984.0, "max": 34165.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7029755998675415, "min": -1.0000000521540642, "max": 1.7886716305319943, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 209.46599878370762, "min": -31.994001641869545, "max": 248.88599736243486, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7029755998675415, "min": -1.0000000521540642, "max": 1.7886716305319943, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 209.46599878370762, "min": -31.994001641869545, "max": 248.88599736243486, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01874860980000434, "min": 0.016304011354424882, "max": 8.773146278224885, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.306079005400534, "min": 2.1763417135662166, "max": 140.37034045159817, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707641308", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Pyramids Training1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707648508" }, "total": 7200.284822367, "count": 1, "self": 0.5284415239993905, "children": { "run_training.setup": { "total": 0.04663787100025729, "count": 1, "self": 0.04663787100025729 }, "TrainerController.start_learning": { "total": 7199.709742972, "count": 1, "self": 3.8992054161790293, "children": { "TrainerController._reset_env": { "total": 2.402931795999848, "count": 1, "self": 2.402931795999848 }, "TrainerController.advance": { "total": 7193.320404859821, "count": 194307, "self": 4.170448085907083, "children": { "env_step": { "total": 5290.6202441470305, "count": 194307, "self": 4909.299461818357, "children": { "SubprocessEnvManager._take_step": { "total": 378.82628616780494, "count": 194307, "self": 13.983717686802265, "children": { "TorchPolicy.evaluate": { "total": 364.8425684810027, "count": 187561, "self": 364.8425684810027 } } }, "workers": { "total": 2.4944961608684935, "count": 194307, "self": 0.0, "children": { "worker_root": { "total": 7184.112410649101, "count": 194307, "is_parallel": true, "self": 2629.682749757172, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020520140001281106, "count": 1, "is_parallel": true, "self": 0.0006502109999928507, "children": { "_process_rank_one_or_two_observation": { "total": 0.00140180300013526, "count": 8, "is_parallel": true, "self": 0.00140180300013526 } } }, "UnityEnvironment.step": { "total": 0.048373163000178465, "count": 1, "is_parallel": true, "self": 0.0005794289995719737, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045700100008616573, "count": 1, "is_parallel": true, "self": 0.00045700100008616573 }, "communicator.exchange": { "total": 0.045748019000257045, "count": 1, "is_parallel": true, "self": 0.045748019000257045 }, "steps_from_proto": { "total": 0.0015887140002632805, "count": 1, "is_parallel": true, "self": 0.0003393910001250333, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012493230001382472, "count": 8, "is_parallel": true, "self": 0.0012493230001382472 } } } } } } }, "UnityEnvironment.step": { "total": 4554.4296608919285, "count": 194306, "is_parallel": true, "self": 106.7503921042935, "children": { "UnityEnvironment._generate_step_input": { "total": 72.42947624292219, "count": 194306, "is_parallel": true, "self": 72.42947624292219 }, "communicator.exchange": { "total": 4077.8874620698484, "count": 194306, "is_parallel": true, "self": 4077.8874620698484 }, "steps_from_proto": { "total": 297.3623304748644, "count": 194306, "is_parallel": true, "self": 58.62167341188933, "children": { "_process_rank_one_or_two_observation": { "total": 238.74065706297506, "count": 1554448, "is_parallel": true, "self": 238.74065706297506 } } } } } } } } } } }, "trainer_advance": { "total": 1898.5297126268833, "count": 194307, "self": 8.17209160847733, "children": { "process_trajectory": { "total": 386.30167562139377, "count": 194307, "self": 385.7367878713944, "children": { "RLTrainer._checkpoint": { "total": 0.5648877499993432, "count": 6, "self": 0.5648877499993432 } } }, "_update_policy": { "total": 1504.0559453970122, "count": 1397, "self": 890.0737098281561, "children": { "TorchPPOOptimizer.update": { "total": 613.9822355688561, "count": 68412, "self": 613.9822355688561 } } } } } } }, "trainer_threads": { "total": 1.0180010576732457e-06, "count": 1, "self": 1.0180010576732457e-06 }, "TrainerController._save_models": { "total": 0.0871998819984583, "count": 1, "self": 0.0015097789982974064, "children": { "RLTrainer._checkpoint": { "total": 0.08569010300016089, "count": 1, "self": 0.08569010300016089 } } } } } } }