{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35756173729896545, "min": 0.35254934430122375, "max": 1.5066057443618774, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10846.9931640625, "min": 10533.35546875, "max": 45704.390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29952.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3797052502632141, "min": -0.09596633166074753, "max": 0.44829073548316956, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 98.7233657836914, "min": -23.223852157592773, "max": 121.48678588867188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025256171822547913, "min": -0.025717997923493385, "max": 0.16532054543495178, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.5666046142578125, "min": -6.455217361450195, "max": 39.18096923828125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06525615897927699, "min": 0.06472599649264123, "max": 0.07560378394245512, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9135862257098779, "min": 0.49793026089315684, "max": 1.0584529751943716, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010093762087871298, "min": 0.001006706680580413, "max": 0.011073197464914603, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14131266923019817, "min": 0.01308718684754537, "max": 0.1607818079307132, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.557526052285716e-06, "min": 7.557526052285716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010580536473200002, "min": 0.00010580536473200002, "max": 0.0036333937888688, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251914285714284, "min": 0.10251914285714284, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352679999999998, "min": 1.3886848, "max": 2.611131200000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002616623714285715, "min": 0.0002616623714285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036632732000000012, "min": 0.0036632732000000012, "max": 0.12113200688, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007462288718670607, "min": 0.007418777793645859, "max": 0.2794453501701355, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10447204113006592, "min": 0.10386288911104202, "max": 1.9561173915863037, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 470.8448275862069, "min": 426.3421052631579, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27309.0, "min": 15984.0, "max": 34753.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2489457429718163, "min": -1.0000000521540642, "max": 1.4361786430080732, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 73.68779883533716, "min": -28.84100167453289, "max": 107.71339822560549, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2489457429718163, "min": -1.0000000521540642, "max": 1.4361786430080732, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 73.68779883533716, "min": -28.84100167453289, "max": 107.71339822560549, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0364751645415169, "min": 0.03459986108022609, "max": 5.91924156434834, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.152034707949497, "min": 2.152034707949497, "max": 94.70786502957344, "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": "1704604761", "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 Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704607068" }, "total": 2307.772790555, "count": 1, "self": 0.47722021399977166, "children": { "run_training.setup": { "total": 0.052840837000076135, "count": 1, "self": 0.052840837000076135 }, "TrainerController.start_learning": { "total": 2307.242729504, "count": 1, "self": 1.6562200650323575, "children": { "TrainerController._reset_env": { "total": 1.9882843140001114, "count": 1, "self": 1.9882843140001114 }, "TrainerController.advance": { "total": 2303.5135463529678, "count": 63598, "self": 1.6787391680154542, "children": { "env_step": { "total": 1641.2701765309607, "count": 63598, "self": 1494.9501485319668, "children": { "SubprocessEnvManager._take_step": { "total": 145.3066577480506, "count": 63598, "self": 5.14844194699981, "children": { "TorchPolicy.evaluate": { "total": 140.1582158010508, "count": 62569, "self": 140.1582158010508 } } }, "workers": { "total": 1.0133702509433533, "count": 63598, "self": 0.0, "children": { "worker_root": { "total": 2301.512000554993, "count": 63598, "is_parallel": true, "self": 937.824281582014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017246590000468132, "count": 1, "is_parallel": true, "self": 0.0005495890002293891, "children": { "_process_rank_one_or_two_observation": { "total": 0.001175069999817424, "count": 8, "is_parallel": true, "self": 0.001175069999817424 } } }, "UnityEnvironment.step": { "total": 0.05288674600001286, "count": 1, "is_parallel": true, "self": 0.0006310139997367514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005027370000334486, "count": 1, "is_parallel": true, "self": 0.0005027370000334486 }, "communicator.exchange": { "total": 0.05003439800020715, "count": 1, "is_parallel": true, "self": 0.05003439800020715 }, "steps_from_proto": { "total": 0.0017185970000355155, "count": 1, "is_parallel": true, "self": 0.0003517459997510741, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013668510002844414, "count": 8, "is_parallel": true, "self": 0.0013668510002844414 } } } } } } }, "UnityEnvironment.step": { "total": 1363.687718972979, "count": 63597, "is_parallel": true, "self": 36.65025568389842, "children": { "UnityEnvironment._generate_step_input": { "total": 26.640481193030837, "count": 63597, "is_parallel": true, "self": 26.640481193030837 }, "communicator.exchange": { "total": 1192.0340881270204, "count": 63597, "is_parallel": true, "self": 1192.0340881270204 }, "steps_from_proto": { "total": 108.3628939690293, "count": 63597, "is_parallel": true, "self": 22.704955567909792, "children": { "_process_rank_one_or_two_observation": { "total": 85.65793840111951, "count": 508776, "is_parallel": true, "self": 85.65793840111951 } } } } } } } } } } }, "trainer_advance": { "total": 660.5646306539918, "count": 63598, "self": 3.1169219970433915, "children": { "process_trajectory": { "total": 134.2382949799469, "count": 63598, "self": 134.03501752594707, "children": { "RLTrainer._checkpoint": { "total": 0.20327745399981723, "count": 2, "self": 0.20327745399981723 } } }, "_update_policy": { "total": 523.2094136770015, "count": 452, "self": 309.7505712369955, "children": { "TorchPPOOptimizer.update": { "total": 213.45884244000604, "count": 22815, "self": 213.45884244000604 } } } } } } }, "trainer_threads": { "total": 1.3599997146229725e-06, "count": 1, "self": 1.3599997146229725e-06 }, "TrainerController._save_models": { "total": 0.0846774120000191, "count": 1, "self": 0.0015345730002991331, "children": { "RLTrainer._checkpoint": { "total": 0.08314283899971997, "count": 1, "self": 0.08314283899971997 } } } } } } }