{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41924169659614563, "min": 0.41924169659614563, "max": 1.4155577421188354, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12577.2509765625, "min": 12577.2509765625, "max": 42942.359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29940.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29940.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6595845222473145, "min": -0.09465137869119644, "max": 0.6595845222473145, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 189.30076599121094, "min": -22.716331481933594, "max": 189.30076599121094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009609554894268513, "min": -0.01311143022030592, "max": 0.39965641498565674, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7579421997070312, "min": -3.7236461639404297, "max": 94.71856689453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06775980816877487, "min": 0.06495583251901936, "max": 0.07354222463202728, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9486373143628483, "min": 0.482093068393049, "max": 1.0350993303964415, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012360608978991562, "min": 0.0007766169070771979, "max": 0.016004003332113676, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17304852570588186, "min": 0.009319402884926374, "max": 0.24006004998170516, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.681318868164283e-06, "min": 7.681318868164283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010753846415429997, "min": 0.00010753846415429997, "max": 0.0035075948308017995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256040714285716, "min": 0.10256040714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358457000000002, "min": 1.3886848, "max": 2.5691982, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026578467357142853, "min": 0.00026578467357142853, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037209854299999996, "min": 0.0037209854299999996, "max": 0.11694290018000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009326353669166565, "min": 0.009326353669166565, "max": 0.4880388081073761, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1305689513683319, "min": 0.1305689513683319, "max": 3.416271686553955, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.02197802197804, "min": 283.8173076923077, "max": 997.28125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29850.0, "min": 16867.0, "max": 32513.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6043644259373346, "min": -0.9356750512961298, "max": 1.658474985581751, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.39279833436012, "min": -30.196201622486115, "max": 172.4813985005021, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6043644259373346, "min": -0.9356750512961298, "max": 1.658474985581751, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.39279833436012, "min": -30.196201622486115, "max": 172.4813985005021, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03128810899442114, "min": 0.03022513236387917, "max": 9.260438284453224, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.815929809497902, "min": 2.815929809497902, "max": 157.4274508357048, "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": "1793539033", "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]", "command_line_arguments": "/content/mlenv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1793541628" }, "total": 2594.991999728, "count": 1, "self": 0.4815511179999703, "children": { "run_training.setup": { "total": 0.023443799999995463, "count": 1, "self": 0.023443799999995463 }, "TrainerController.start_learning": { "total": 2594.48700481, "count": 1, "self": 1.791485061961339, "children": { "TrainerController._reset_env": { "total": 2.2836227310001505, "count": 1, "self": 2.2836227310001505 }, "TrainerController.advance": { "total": 2590.3195602000383, "count": 63866, "self": 1.8456350509190997, "children": { "env_step": { "total": 1890.9878960899898, "count": 63866, "self": 1705.9875602949774, "children": { "SubprocessEnvManager._take_step": { "total": 183.90451553308253, "count": 63866, "self": 5.501308545057327, "children": { "TorchPolicy.evaluate": { "total": 178.4032069880252, "count": 62566, "self": 178.4032069880252 } } }, "workers": { "total": 1.09582026192993, "count": 63866, "self": 0.0, "children": { "worker_root": { "total": 2588.1396855939515, "count": 63866, "is_parallel": true, "self": 1021.633005406874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023454880001736456, "count": 1, "is_parallel": true, "self": 0.0008816030003799824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014638849997936632, "count": 8, "is_parallel": true, "self": 0.0014638849997936632 } } }, "UnityEnvironment.step": { "total": 0.05660898299993278, "count": 1, "is_parallel": true, "self": 0.0005720399999518122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005059060001713078, "count": 1, "is_parallel": true, "self": 0.0005059060001713078 }, "communicator.exchange": { "total": 0.053633381999816265, "count": 1, "is_parallel": true, "self": 0.053633381999816265 }, "steps_from_proto": { "total": 0.0018976549999933923, "count": 1, "is_parallel": true, "self": 0.00040640700035510235, "children": { "_process_rank_one_or_two_observation": { "total": 0.00149124799963829, "count": 8, "is_parallel": true, "self": 0.00149124799963829 } } } } } } }, "UnityEnvironment.step": { "total": 1566.5066801870776, "count": 63865, "is_parallel": true, "self": 37.51282641102307, "children": { "UnityEnvironment._generate_step_input": { "total": 26.178065572056312, "count": 63865, "is_parallel": true, "self": 26.178065572056312 }, "communicator.exchange": { "total": 1377.013139197025, "count": 63865, "is_parallel": true, "self": 1377.013139197025 }, "steps_from_proto": { "total": 125.80264900697307, "count": 63865, "is_parallel": true, "self": 26.59481273008828, "children": { "_process_rank_one_or_two_observation": { "total": 99.20783627688479, "count": 510920, "is_parallel": true, "self": 99.20783627688479 } } } } } } } } } } }, "trainer_advance": { "total": 697.4860290591296, "count": 63866, "self": 3.372340822113074, "children": { "process_trajectory": { "total": 126.94152763702004, "count": 63866, "self": 126.72374804701985, "children": { "RLTrainer._checkpoint": { "total": 0.2177795900001911, "count": 2, "self": 0.2177795900001911 } } }, "_update_policy": { "total": 567.1721605999965, "count": 455, "self": 304.79854033601623, "children": { "TorchPPOOptimizer.update": { "total": 262.37362026398023, "count": 22782, "self": 262.37362026398023 } } } } } } }, "trainer_threads": { "total": 8.739998520468362e-07, "count": 1, "self": 8.739998520468362e-07 }, "TrainerController._save_models": { "total": 0.09233594300030745, "count": 1, "self": 0.0010601960002531996, "children": { "RLTrainer._checkpoint": { "total": 0.09127574700005425, "count": 1, "self": 0.09127574700005425 } } } } } } }