{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3870369493961334, "min": 0.3870369493961334, "max": 1.4080069065093994, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11561.5673828125, "min": 11561.5673828125, "max": 42713.296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5696612000465393, "min": -0.07832173258066177, "max": 0.6059459447860718, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.36581420898438, "min": -18.875537872314453, "max": 168.45297241210938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0012085920898243785, "min": 0.0012085920898243785, "max": 0.29519596695899963, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.3359886109828949, "min": 0.3359886109828949, "max": 71.05264282226562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06514077692866392, "min": 0.06391433600774257, "max": 0.07325277906072257, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9119708770012949, "min": 0.512769453425058, "max": 1.0481821497766455, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014526769909675096, "min": 0.0008138491339818827, "max": 0.016351179136998125, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20337477873545134, "min": 0.00895234047380071, "max": 0.24526768705497187, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4178975273999975e-06, "min": 7.4178975273999975e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010385056538359997, "min": 0.00010385056538359997, "max": 0.0035080115306628996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247260000000001, "min": 0.10247260000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346164000000001, "min": 1.3886848, "max": 2.5693371000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025701273999999996, "min": 0.00025701273999999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035981783599999995, "min": 0.0035981783599999995, "max": 0.11695677629, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011082448065280914, "min": 0.011082448065280914, "max": 0.49767225980758667, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1551542729139328, "min": 0.1551542729139328, "max": 3.483705759048462, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.5111111111111, "min": 310.77319587628864, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31546.0, "min": 15984.0, "max": 33066.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5605822121103605, "min": -1.0000000521540642, "max": 1.6686061748217063, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.45239908993244, "min": -30.188401713967323, "max": 161.8547989577055, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5605822121103605, "min": -1.0000000521540642, "max": 1.6686061748217063, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.45239908993244, "min": -30.188401713967323, "max": 161.8547989577055, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0395769118877878, "min": 0.03779605594969134, "max": 10.006938023492694, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.561922069900902, "min": 3.3419187057734234, "max": 160.1110083758831, "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": "1711113180", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711116658" }, "total": 3477.3743351500007, "count": 1, "self": 0.6453852040003767, "children": { "run_training.setup": { "total": 0.11155739699984224, "count": 1, "self": 0.11155739699984224 }, "TrainerController.start_learning": { "total": 3476.617392549, "count": 1, "self": 2.371446346920493, "children": { "TrainerController._reset_env": { "total": 3.8616913309999745, "count": 1, "self": 3.8616913309999745 }, "TrainerController.advance": { "total": 3470.2984072740787, "count": 63918, "self": 2.6609598620993893, "children": { "env_step": { "total": 2321.279286810013, "count": 63918, "self": 2151.3800145021437, "children": { "SubprocessEnvManager._take_step": { "total": 168.36165376385225, "count": 63918, "self": 7.423675920872029, "children": { "TorchPolicy.evaluate": { "total": 160.93797784298022, "count": 62569, "self": 160.93797784298022 } } }, "workers": { "total": 1.5376185440172776, "count": 63918, "self": 0.0, "children": { "worker_root": { "total": 3470.1297319270184, "count": 63918, "is_parallel": true, "self": 1511.3299455508104, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005445891999897867, "count": 1, "is_parallel": true, "self": 0.0015724959994258825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038733960004719847, "count": 8, "is_parallel": true, "self": 0.0038733960004719847 } } }, "UnityEnvironment.step": { "total": 0.08437621300004139, "count": 1, "is_parallel": true, "self": 0.0009459980001338408, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000590620999901148, "count": 1, "is_parallel": true, "self": 0.000590620999901148 }, "communicator.exchange": { "total": 0.0806891810000252, "count": 1, "is_parallel": true, "self": 0.0806891810000252 }, "steps_from_proto": { "total": 0.0021504129999811994, "count": 1, "is_parallel": true, "self": 0.00048611399961373536, "children": { "_process_rank_one_or_two_observation": { "total": 0.001664299000367464, "count": 8, "is_parallel": true, "self": 0.001664299000367464 } } } } } } }, "UnityEnvironment.step": { "total": 1958.799786376208, "count": 63917, "is_parallel": true, "self": 52.43495547028715, "children": { "UnityEnvironment._generate_step_input": { "total": 29.377315622935384, "count": 63917, "is_parallel": true, "self": 29.377315622935384 }, "communicator.exchange": { "total": 1742.8378438999582, "count": 63917, "is_parallel": true, "self": 1742.8378438999582 }, "steps_from_proto": { "total": 134.14967138302723, "count": 63917, "is_parallel": true, "self": 28.91528011919445, "children": { "_process_rank_one_or_two_observation": { "total": 105.23439126383278, "count": 511336, "is_parallel": true, "self": 105.23439126383278 } } } } } } } } } } }, "trainer_advance": { "total": 1146.3581606019661, "count": 63918, "self": 5.012123507923434, "children": { "process_trajectory": { "total": 176.07172657803403, "count": 63918, "self": 175.73485912603428, "children": { "RLTrainer._checkpoint": { "total": 0.3368674519997512, "count": 2, "self": 0.3368674519997512 } } }, "_update_policy": { "total": 965.2743105160087, "count": 451, "self": 378.38823975400555, "children": { "TorchPPOOptimizer.update": { "total": 586.8860707620031, "count": 22803, "self": 586.8860707620031 } } } } } } }, "trainer_threads": { "total": 1.076000444300007e-06, "count": 1, "self": 1.076000444300007e-06 }, "TrainerController._save_models": { "total": 0.08584652100034873, "count": 1, "self": 0.0022218720005184878, "children": { "RLTrainer._checkpoint": { "total": 0.08362464899983024, "count": 1, "self": 0.08362464899983024 } } } } } } }