{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3562077283859253, "min": 0.35026243329048157, "max": 1.4727118015289307, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10566.5458984375, "min": 10566.5458984375, "max": 44676.18359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6090155839920044, "min": -0.1051861122250557, "max": 0.6592516303062439, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 169.91534423828125, "min": -25.349853515625, "max": 185.90896606445312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017709024250507355, "min": 0.007463117595762014, "max": 0.4340612292289734, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.940817832946777, "min": 2.1120622158050537, "max": 102.87251281738281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06814465523417484, "min": 0.06549656122962814, "max": 0.07313228384844835, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9540251732784478, "min": 0.5109224383195397, "max": 1.067510117936763, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01640730622914686, "min": 0.0013034059444631877, "max": 0.01640730622914686, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22970228720805605, "min": 0.011777948948669103, "max": 0.22970228720805605, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.545033199307142e-06, "min": 7.545033199307142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010563046479029999, "min": 0.00010563046479029999, "max": 0.003507042230986, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251497857142858, "min": 0.10251497857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352097000000001, "min": 1.3886848, "max": 2.5690140000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002612463592857143, "min": 0.0002612463592857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036574490300000004, "min": 0.0036574490300000004, "max": 0.1169244986, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015620983205735683, "min": 0.015298821963369846, "max": 0.6473064422607422, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21869376301765442, "min": 0.214183509349823, "max": 4.531145095825195, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 315.78125, "min": 278.2352941176471, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30315.0, "min": 15984.0, "max": 32653.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6842187337266903, "min": -1.0000000521540642, "max": 1.7221187987540028, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 161.68499843776226, "min": -30.68500165641308, "max": 173.93399867415428, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6842187337266903, "min": -1.0000000521540642, "max": 1.7221187987540028, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 161.68499843776226, "min": -30.68500165641308, "max": 173.93399867415428, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05129864022183028, "min": 0.047025082037567466, "max": 13.05104298144579, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.924669461295707, "min": 4.749533285794314, "max": 208.81668770313263, "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": "1716895967", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716899386" }, "total": 3419.247537036, "count": 1, "self": 0.7983501699995941, "children": { "run_training.setup": { "total": 0.07234970299998622, "count": 1, "self": 0.07234970299998622 }, "TrainerController.start_learning": { "total": 3418.3768371630003, "count": 1, "self": 2.30618902402648, "children": { "TrainerController._reset_env": { "total": 3.3823001700000077, "count": 1, "self": 3.3823001700000077 }, "TrainerController.advance": { "total": 3412.591203232974, "count": 64015, "self": 2.418622981025237, "children": { "env_step": { "total": 2294.25827542899, "count": 64015, "self": 2126.9066876479164, "children": { "SubprocessEnvManager._take_step": { "total": 165.98362832905957, "count": 64015, "self": 6.9563613651267815, "children": { "TorchPolicy.evaluate": { "total": 159.0272669639328, "count": 62561, "self": 159.0272669639328 } } }, "workers": { "total": 1.3679594520140768, "count": 64015, "self": 0.0, "children": { "worker_root": { "total": 3411.028653390958, "count": 64015, "is_parallel": true, "self": 1471.1778895309953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005720887999984825, "count": 1, "is_parallel": true, "self": 0.004073775999870577, "children": { "_process_rank_one_or_two_observation": { "total": 0.001647112000114248, "count": 8, "is_parallel": true, "self": 0.001647112000114248 } } }, "UnityEnvironment.step": { "total": 0.062275051000028725, "count": 1, "is_parallel": true, "self": 0.0007918279999898914, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005340899999737303, "count": 1, "is_parallel": true, "self": 0.0005340899999737303 }, "communicator.exchange": { "total": 0.058974425000030806, "count": 1, "is_parallel": true, "self": 0.058974425000030806 }, "steps_from_proto": { "total": 0.0019747080000342976, "count": 1, "is_parallel": true, "self": 0.0004407609999930173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015339470000412803, "count": 8, "is_parallel": true, "self": 0.0015339470000412803 } } } } } } }, "UnityEnvironment.step": { "total": 1939.8507638599626, "count": 64014, "is_parallel": true, "self": 50.92613256382174, "children": { "UnityEnvironment._generate_step_input": { "total": 30.897700307064497, "count": 64014, "is_parallel": true, "self": 30.897700307064497 }, "communicator.exchange": { "total": 1727.782795491028, "count": 64014, "is_parallel": true, "self": 1727.782795491028 }, "steps_from_proto": { "total": 130.2441354980483, "count": 64014, "is_parallel": true, "self": 28.20794342290651, "children": { "_process_rank_one_or_two_observation": { "total": 102.0361920751418, "count": 512112, "is_parallel": true, "self": 102.0361920751418 } } } } } } } } } } }, "trainer_advance": { "total": 1115.9143048229587, "count": 64015, "self": 4.5206448780090795, "children": { "process_trajectory": { "total": 169.6984079059526, "count": 64015, "self": 169.3780220119525, "children": { "RLTrainer._checkpoint": { "total": 0.32038589400008277, "count": 2, "self": 0.32038589400008277 } } }, "_update_policy": { "total": 941.6952520389971, "count": 449, "self": 379.349913138024, "children": { "TorchPPOOptimizer.update": { "total": 562.345338900973, "count": 22833, "self": 562.345338900973 } } } } } } }, "trainer_threads": { "total": 1.1130000530101825e-06, "count": 1, "self": 1.1130000530101825e-06 }, "TrainerController._save_models": { "total": 0.09714362300019275, "count": 1, "self": 0.0038617130003331113, "children": { "RLTrainer._checkpoint": { "total": 0.09328190999985964, "count": 1, "self": 0.09328190999985964 } } } } } } }