{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37050753831863403, "min": 0.37050753831863403, "max": 1.5090738534927368, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11162.6513671875, "min": 11162.6513671875, "max": 45779.265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5849660634994507, "min": -0.09617185592651367, "max": 0.5849660634994507, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.6205596923828, "min": -23.177417755126953, "max": 162.6205596923828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.12547501921653748, "min": -0.12547501921653748, "max": 0.33637240529060364, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -34.882057189941406, "min": -34.882057189941406, "max": 81.06575012207031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07045742286008382, "min": 0.06330401496150555, "max": 0.07423567600244381, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9864039200411734, "min": 0.49262263935866185, "max": 1.0351983988172528, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016304492073248373, "min": 0.0009629485244299622, "max": 0.017009932760427345, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2282628890254772, "min": 0.011470983480419727, "max": 0.2551489914064102, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.775325979685713e-06, "min": 7.775325979685713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010885456371559998, "min": 0.00010885456371559998, "max": 0.0033766183744605993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259174285714288, "min": 0.10259174285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362844000000003, "min": 1.3886848, "max": 2.4434973, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002689151114285714, "min": 0.0002689151114285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037648115599999998, "min": 0.0037648115599999998, "max": 0.11257138605999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013374842703342438, "min": 0.013374842703342438, "max": 0.4573424160480499, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18724779784679413, "min": 0.18724779784679413, "max": 3.201396942138672, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 309.5, "min": 309.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28474.0, "min": 15984.0, "max": 32668.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6687499834629504, "min": -1.0000000521540642, "max": 1.6687499834629504, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.52499847859144, "min": -30.699601642787457, "max": 156.55699794739485, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6687499834629504, "min": -1.0000000521540642, "max": 1.6687499834629504, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.52499847859144, "min": -30.699601642787457, "max": 156.55699794739485, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042854938246107296, "min": 0.042854938246107296, "max": 8.986872300505638, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.942654318641871, "min": 3.942654318641871, "max": 143.7899568080902, "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": "1691786572", "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=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": "1691789024" }, "total": 2452.163882346, "count": 1, "self": 0.5285550479998165, "children": { "run_training.setup": { "total": 0.06631402099992556, "count": 1, "self": 0.06631402099992556 }, "TrainerController.start_learning": { "total": 2451.569013277, "count": 1, "self": 1.8040711649482546, "children": { "TrainerController._reset_env": { "total": 4.22959266099997, "count": 1, "self": 4.22959266099997 }, "TrainerController.advance": { "total": 2445.435050946052, "count": 63749, "self": 1.7881953101118597, "children": { "env_step": { "total": 1743.1624217469748, "count": 63749, "self": 1610.0631441539513, "children": { "SubprocessEnvManager._take_step": { "total": 132.05706206003197, "count": 63749, "self": 5.430805084046824, "children": { "TorchPolicy.evaluate": { "total": 126.62625697598514, "count": 62544, "self": 126.62625697598514 } } }, "workers": { "total": 1.0422155329915768, "count": 63749, "self": 0.0, "children": { "worker_root": { "total": 2444.9891518690697, "count": 63749, "is_parallel": true, "self": 973.5911753850874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017736280001372506, "count": 1, "is_parallel": true, "self": 0.0005434949998743832, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012301330002628674, "count": 8, "is_parallel": true, "self": 0.0012301330002628674 } } }, "UnityEnvironment.step": { "total": 0.05531749000010677, "count": 1, "is_parallel": true, "self": 0.0006538560005537875, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004950919997099845, "count": 1, "is_parallel": true, "self": 0.0004950919997099845 }, "communicator.exchange": { "total": 0.05195667799989678, "count": 1, "is_parallel": true, "self": 0.05195667799989678 }, "steps_from_proto": { "total": 0.0022118639999462175, "count": 1, "is_parallel": true, "self": 0.0005090370000289113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017028269999173062, "count": 8, "is_parallel": true, "self": 0.0017028269999173062 } } } } } } }, "UnityEnvironment.step": { "total": 1471.3979764839823, "count": 63748, "is_parallel": true, "self": 37.28450710791958, "children": { "UnityEnvironment._generate_step_input": { "total": 26.250771246994645, "count": 63748, "is_parallel": true, "self": 26.250771246994645 }, "communicator.exchange": { "total": 1286.862065579141, "count": 63748, "is_parallel": true, "self": 1286.862065579141 }, "steps_from_proto": { "total": 121.0006325499271, "count": 63748, "is_parallel": true, "self": 24.77178807888231, "children": { "_process_rank_one_or_two_observation": { "total": 96.2288444710448, "count": 509984, "is_parallel": true, "self": 96.2288444710448 } } } } } } } } } } }, "trainer_advance": { "total": 700.4844338889652, "count": 63749, "self": 3.2357902739850033, "children": { "process_trajectory": { "total": 125.19278267199206, "count": 63749, "self": 124.97284019799281, "children": { "RLTrainer._checkpoint": { "total": 0.2199424739992537, "count": 2, "self": 0.2199424739992537 } } }, "_update_policy": { "total": 572.0558609429881, "count": 448, "self": 374.4386337700348, "children": { "TorchPPOOptimizer.update": { "total": 197.61722717295333, "count": 22800, "self": 197.61722717295333 } } } } } } }, "trainer_threads": { "total": 1.2339996828814037e-06, "count": 1, "self": 1.2339996828814037e-06 }, "TrainerController._save_models": { "total": 0.1002972710002723, "count": 1, "self": 0.0014350070005093585, "children": { "RLTrainer._checkpoint": { "total": 0.09886226399976294, "count": 1, "self": 0.09886226399976294 } } } } } } }