{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.24153396487236023, "min": 0.22872592508792877, "max": 1.3258540630340576, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7269.2060546875, "min": 6913.01220703125, "max": 40221.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5765137076377869, "min": -0.12130161374807358, "max": 0.6815979480743408, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.30641174316406, "min": -29.233688354492188, "max": 190.84742736816406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0018550094682723284, "min": -0.0379815399646759, "max": 0.5097795724868774, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.5286777019500732, "min": -10.748775482177734, "max": 120.81775665283203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06653714150742104, "min": 0.06386972728481605, "max": 0.07280471996051639, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9315199811038946, "min": 0.5096330397236147, "max": 1.0475896541457215, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017914707432746403, "min": 0.0009683842048086596, "max": 0.025699071040656257, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25080590405844966, "min": 0.011620610457703915, "max": 0.25080590405844966, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5662046208214304e-06, "min": 7.5662046208214304e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010592686469150003, "min": 0.00010592686469150003, "max": 0.0036326128891290997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252203571428568, "min": 0.10252203571428568, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353084999999997, "min": 1.3886848, "max": 2.6626006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026195136785714303, "min": 0.00026195136785714303, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036673191500000025, "min": 0.0036673191500000025, "max": 0.12110600290999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011418631300330162, "min": 0.011418631300330162, "max": 0.5888192057609558, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15986083447933197, "min": 0.15986083447933197, "max": 4.121734619140625, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 315.66, "min": 290.9805825242718, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31566.0, "min": 15984.0, "max": 33144.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.561579783080202, "min": -1.0000000521540642, "max": 1.6543591237196358, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 154.59639852494, "min": -27.17300169914961, "max": 168.40919855237007, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.561579783080202, "min": -1.0000000521540642, "max": 1.6543591237196358, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 154.59639852494, "min": -27.17300169914961, "max": 168.40919855237007, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03812256277094341, "min": 0.03812256277094341, "max": 13.275423040613532, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7741337143233977, "min": 3.339011607487919, "max": 212.4067686498165, "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": "1682090665", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1682093650" }, "total": 2984.6821275520006, "count": 1, "self": 0.5381241890004276, "children": { "run_training.setup": { "total": 0.22867667399987113, "count": 1, "self": 0.22867667399987113 }, "TrainerController.start_learning": { "total": 2983.9153266890003, "count": 1, "self": 1.9758146279887114, "children": { "TrainerController._reset_env": { "total": 1.544041112000059, "count": 1, "self": 1.544041112000059 }, "TrainerController.advance": { "total": 2980.299251860011, "count": 64204, "self": 2.0125228480769692, "children": { "env_step": { "total": 1976.2768917709627, "count": 64204, "self": 1860.604449555043, "children": { "SubprocessEnvManager._take_step": { "total": 114.45081119503084, "count": 64204, "self": 5.717343049034753, "children": { "TorchPolicy.evaluate": { "total": 108.73346814599608, "count": 62568, "self": 108.73346814599608 } } }, "workers": { "total": 1.2216310208889354, "count": 64204, "self": 0.0, "children": { "worker_root": { "total": 2977.6490727499568, "count": 64204, "is_parallel": true, "self": 1258.9524269889012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00630627500004266, "count": 1, "is_parallel": true, "self": 0.0037305200000901095, "children": { "_process_rank_one_or_two_observation": { "total": 0.002575754999952551, "count": 8, "is_parallel": true, "self": 0.002575754999952551 } } }, "UnityEnvironment.step": { "total": 0.09882036099998004, "count": 1, "is_parallel": true, "self": 0.0006204639996667538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007167270000536519, "count": 1, "is_parallel": true, "self": 0.0007167270000536519 }, "communicator.exchange": { "total": 0.09548942300011731, "count": 1, "is_parallel": true, "self": 0.09548942300011731 }, "steps_from_proto": { "total": 0.0019937470001423208, "count": 1, "is_parallel": true, "self": 0.00046859799954290793, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015251490005994128, "count": 8, "is_parallel": true, "self": 0.0015251490005994128 } } } } } } }, "UnityEnvironment.step": { "total": 1718.6966457610556, "count": 64203, "is_parallel": true, "self": 39.47921633006945, "children": { "UnityEnvironment._generate_step_input": { "total": 23.503173016007622, "count": 64203, "is_parallel": true, "self": 23.503173016007622 }, "communicator.exchange": { "total": 1534.9625873140087, "count": 64203, "is_parallel": true, "self": 1534.9625873140087 }, "steps_from_proto": { "total": 120.75166910096982, "count": 64203, "is_parallel": true, "self": 26.991463324992765, "children": { "_process_rank_one_or_two_observation": { "total": 93.76020577597706, "count": 513624, "is_parallel": true, "self": 93.76020577597706 } } } } } } } } } } }, "trainer_advance": { "total": 1002.0098372409714, "count": 64204, "self": 3.6026901560283022, "children": { "process_trajectory": { "total": 129.75619862193844, "count": 64204, "self": 129.54685010893854, "children": { "RLTrainer._checkpoint": { "total": 0.20934851299989532, "count": 2, "self": 0.20934851299989532 } } }, "_update_policy": { "total": 868.6509484630046, "count": 456, "self": 376.02351777597437, "children": { "TorchPPOOptimizer.update": { "total": 492.62743068703026, "count": 22815, "self": 492.62743068703026 } } } } } } }, "trainer_threads": { "total": 1.2250002328073606e-06, "count": 1, "self": 1.2250002328073606e-06 }, "TrainerController._save_models": { "total": 0.09621786400020937, "count": 1, "self": 0.001657392000197433, "children": { "RLTrainer._checkpoint": { "total": 0.09456047200001194, "count": 1, "self": 0.09456047200001194 } } } } } } }