{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45511460304260254, "min": 0.45511460304260254, "max": 1.4204320907592773, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13813.638671875, "min": 13779.55078125, "max": 43090.2265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6417292952537537, "min": -0.09549913555383682, "max": 0.6933141946792603, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.89285278320312, "min": -22.91979217529297, "max": 199.6744842529297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019893599674105644, "min": -0.02651064656674862, "max": 0.3611195385456085, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.669675827026367, "min": -7.369959831237793, "max": 87.39093017578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07071723184134399, "min": 0.06476677235558952, "max": 0.0739571617020937, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0607584776201597, "min": 0.4849838160178102, "max": 1.0734762682889898, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015304262354685409, "min": 0.00017715715563074413, "max": 0.01778547307059002, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22956393532028113, "min": 0.0021258858675689296, "max": 0.2565344411619555, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.468677510473335e-06, "min": 7.468677510473335e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011203016265710002, "min": 0.00011203016265710002, "max": 0.003330197189934299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248952666666668, "min": 0.10248952666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373429, "min": 1.3886848, "max": 2.4018628000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002587037140000001, "min": 0.0002587037140000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003880555710000002, "min": 0.003880555710000002, "max": 0.11101556343, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012898260727524757, "min": 0.012898260727524757, "max": 0.5469852089881897, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1934739053249359, "min": 0.1843286007642746, "max": 3.8288962841033936, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 297.747572815534, "min": 280.3703703703704, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30668.0, "min": 15984.0, "max": 32545.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6439747427707736, "min": -1.0000000521540642, "max": 1.7200275112729553, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 169.3293985053897, "min": -31.99640165269375, "max": 187.48299872875214, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6439747427707736, "min": -1.0000000521540642, "max": 1.7200275112729553, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 169.3293985053897, "min": -31.99640165269375, "max": 187.48299872875214, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04000237750859774, "min": 0.03856092089613036, "max": 10.661596650257707, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.120244883385567, "min": 3.86201220395742, "max": 170.5855464041233, "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": "1690354013", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690356313" }, "total": 2299.756992256, "count": 1, "self": 0.5432933340002819, "children": { "run_training.setup": { "total": 0.037338524000006146, "count": 1, "self": 0.037338524000006146 }, "TrainerController.start_learning": { "total": 2299.176360398, "count": 1, "self": 1.3805928990086613, "children": { "TrainerController._reset_env": { "total": 5.956251769999994, "count": 1, "self": 5.956251769999994 }, "TrainerController.advance": { "total": 2291.7421100209913, "count": 63942, "self": 1.4319647459515181, "children": { "env_step": { "total": 1619.3997202970113, "count": 63942, "self": 1508.9185242400122, "children": { "SubprocessEnvManager._take_step": { "total": 109.65075589404671, "count": 63942, "self": 4.798881735027749, "children": { "TorchPolicy.evaluate": { "total": 104.85187415901896, "count": 62556, "self": 104.85187415901896 } } }, "workers": { "total": 0.8304401629522999, "count": 63942, "self": 0.0, "children": { "worker_root": { "total": 2293.993994102, "count": 63942, "is_parallel": true, "self": 902.8126096660251, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005501332000051207, "count": 1, "is_parallel": true, "self": 0.004126317000100244, "children": { "_process_rank_one_or_two_observation": { "total": 0.001375014999950963, "count": 8, "is_parallel": true, "self": 0.001375014999950963 } } }, "UnityEnvironment.step": { "total": 0.056391374000043015, "count": 1, "is_parallel": true, "self": 0.0005854890000591695, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000506980000011481, "count": 1, "is_parallel": true, "self": 0.000506980000011481 }, "communicator.exchange": { "total": 0.053444995000006656, "count": 1, "is_parallel": true, "self": 0.053444995000006656 }, "steps_from_proto": { "total": 0.0018539099999657083, "count": 1, "is_parallel": true, "self": 0.0004192339999349315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014346760000307768, "count": 8, "is_parallel": true, "self": 0.0014346760000307768 } } } } } } }, "UnityEnvironment.step": { "total": 1391.1813844359751, "count": 63941, "is_parallel": true, "self": 35.62400667295901, "children": { "UnityEnvironment._generate_step_input": { "total": 23.48254349598693, "count": 63941, "is_parallel": true, "self": 23.48254349598693 }, "communicator.exchange": { "total": 1227.2354369170275, "count": 63941, "is_parallel": true, "self": 1227.2354369170275 }, "steps_from_proto": { "total": 104.8393973500016, "count": 63941, "is_parallel": true, "self": 21.38284913399815, "children": { "_process_rank_one_or_two_observation": { "total": 83.45654821600345, "count": 511528, "is_parallel": true, "self": 83.45654821600345 } } } } } } } } } } }, "trainer_advance": { "total": 670.9104249780283, "count": 63942, "self": 2.5342161249742503, "children": { "process_trajectory": { "total": 112.622339006054, "count": 63942, "self": 112.40777748005411, "children": { "RLTrainer._checkpoint": { "total": 0.21456152599989764, "count": 2, "self": 0.21456152599989764 } } }, "_update_policy": { "total": 555.7538698470001, "count": 447, "self": 363.65270011399036, "children": { "TorchPPOOptimizer.update": { "total": 192.10116973300978, "count": 22803, "self": 192.10116973300978 } } } } } } }, "trainer_threads": { "total": 1.0019998626376037e-06, "count": 1, "self": 1.0019998626376037e-06 }, "TrainerController._save_models": { "total": 0.09740470599990658, "count": 1, "self": 0.0014147249999041378, "children": { "RLTrainer._checkpoint": { "total": 0.09598998100000244, "count": 1, "self": 0.09598998100000244 } } } } } } }