{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5080081820487976, "min": 0.5080081820487976, "max": 1.4849011898040771, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15248.3740234375, "min": 15248.3740234375, "max": 45045.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29938.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29938.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.31311851739883423, "min": -0.150189608335495, "max": 0.3262519836425781, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 80.78457641601562, "min": -35.59493637084961, "max": 85.15176391601562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.12348699569702148, "min": -0.12348699569702148, "max": 0.27709341049194336, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -31.85964584350586, "min": -31.85964584350586, "max": 66.5024185180664, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06522595079214727, "min": 0.06498586602814897, "max": 0.07340125930536659, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.978389261882209, "min": 0.5138088151375662, "max": 1.0500581553342807, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017978071982441987, "min": 8.651165985968257e-05, "max": 0.017978071982441987, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2696710797366298, "min": 0.0011246515781758734, "max": 0.2696710797366298, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.493137502320001e-06, "min": 7.493137502320001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011239706253480001, "min": 0.00011239706253480001, "max": 0.0033730411756529998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249768000000001, "min": 0.10249768000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374652000000002, "min": 1.3886848, "max": 2.4243469999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002595182320000001, "min": 0.0002595182320000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003892773480000001, "min": 0.003892773480000001, "max": 0.1124522653, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01341160573065281, "min": 0.013053983449935913, "max": 0.4507472813129425, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2011740803718567, "min": 0.18275576829910278, "max": 3.15523099899292, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 540.7636363636364, "min": 479.8688524590164, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29742.0, "min": 16865.0, "max": 33884.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.058079965954477, "min": -0.999825858300732, "max": 1.2853766394158204, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.19439812749624, "min": -31.994001641869545, "max": 77.12259836494923, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.058079965954477, "min": -0.999825858300732, "max": 1.2853766394158204, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.19439812749624, "min": -31.994001641869545, "max": 77.12259836494923, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07532038811424917, "min": 0.06483432772535404, "max": 8.602985240080777, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.142621346283704, "min": 3.8900596635212423, "max": 146.25074908137321, "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": "1726857553", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726859595" }, "total": 2042.0621460109996, "count": 1, "self": 0.4884440319992791, "children": { "run_training.setup": { "total": 0.04970398600016779, "count": 1, "self": 0.04970398600016779 }, "TrainerController.start_learning": { "total": 2041.5239979930002, "count": 1, "self": 1.2457439880317906, "children": { "TrainerController._reset_env": { "total": 1.8258931270001995, "count": 1, "self": 1.8258931270001995 }, "TrainerController.advance": { "total": 2038.3723219119684, "count": 63267, "self": 1.3062500677369826, "children": { "env_step": { "total": 1362.4883660531377, "count": 63267, "self": 1216.0686482851988, "children": { "SubprocessEnvManager._take_step": { "total": 145.68597462795879, "count": 63267, "self": 4.417087197968613, "children": { "TorchPolicy.evaluate": { "total": 141.26888742999017, "count": 62564, "self": 141.26888742999017 } } }, "workers": { "total": 0.7337431399801062, "count": 63267, "self": 0.0, "children": { "worker_root": { "total": 2036.6728334030477, "count": 63267, "is_parallel": true, "self": 930.1884699449747, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020810989999517915, "count": 1, "is_parallel": true, "self": 0.0006466720014941529, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014344269984576385, "count": 8, "is_parallel": true, "self": 0.0014344269984576385 } } }, "UnityEnvironment.step": { "total": 0.04503517499961163, "count": 1, "is_parallel": true, "self": 0.0006065659990781569, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004736860000775778, "count": 1, "is_parallel": true, "self": 0.0004736860000775778 }, "communicator.exchange": { "total": 0.04239570099980483, "count": 1, "is_parallel": true, "self": 0.04239570099980483 }, "steps_from_proto": { "total": 0.0015592220006510615, "count": 1, "is_parallel": true, "self": 0.00034520100143708987, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012140209992139717, "count": 8, "is_parallel": true, "self": 0.0012140209992139717 } } } } } } }, "UnityEnvironment.step": { "total": 1106.484363458073, "count": 63266, "is_parallel": true, "self": 32.17720018596356, "children": { "UnityEnvironment._generate_step_input": { "total": 22.733265753138767, "count": 63266, "is_parallel": true, "self": 22.733265753138767 }, "communicator.exchange": { "total": 959.8173609839059, "count": 63266, "is_parallel": true, "self": 959.8173609839059 }, "steps_from_proto": { "total": 91.7565365350647, "count": 63266, "is_parallel": true, "self": 18.279492258919163, "children": { "_process_rank_one_or_two_observation": { "total": 73.47704427614553, "count": 506128, "is_parallel": true, "self": 73.47704427614553 } } } } } } } } } } }, "trainer_advance": { "total": 674.5777057910936, "count": 63267, "self": 2.283834877195659, "children": { "process_trajectory": { "total": 126.45099324290277, "count": 63267, "self": 126.05992240190244, "children": { "RLTrainer._checkpoint": { "total": 0.3910708410003281, "count": 2, "self": 0.3910708410003281 } } }, "_update_policy": { "total": 545.8428776709952, "count": 445, "self": 307.9008821729767, "children": { "TorchPPOOptimizer.update": { "total": 237.9419954980185, "count": 22791, "self": 237.9419954980185 } } } } } } }, "trainer_threads": { "total": 9.169998520519584e-07, "count": 1, "self": 9.169998520519584e-07 }, "TrainerController._save_models": { "total": 0.08003804899999523, "count": 1, "self": 0.001366756999232166, "children": { "RLTrainer._checkpoint": { "total": 0.07867129200076306, "count": 1, "self": 0.07867129200076306 } } } } } } }