{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42291876673698425, "min": 0.42291876673698425, "max": 1.5048750638961792, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12660.49609375, "min": 12660.49609375, "max": 45651.890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989933.0, "min": 29934.0, "max": 989933.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989933.0, "min": 29934.0, "max": 989933.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46718940138816833, "min": -0.10759367793798447, "max": 0.4884960949420929, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.07551574707031, "min": -25.930076599121094, "max": 133.84793090820312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07992153614759445, "min": -0.003266091225668788, "max": 0.30502840876579285, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.738656997680664, "min": -0.8295871615409851, "max": 72.29173278808594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07092821263294254, "min": 0.06465869850043894, "max": 0.07264722185985496, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.063923189494138, "min": 0.5031058096424569, "max": 1.0897083278978243, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015976743049557422, "min": 0.0003376336035353093, "max": 0.016785624952985124, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23965114574336135, "min": 0.004389236845959021, "max": 0.23965114574336135, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.520717493126664e-06, "min": 7.520717493126664e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011281076239689996, "min": 0.00011281076239689996, "max": 0.0036322237892588, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250687333333336, "min": 0.10250687333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376031000000003, "min": 1.3886848, "max": 2.6107411999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000260436646, "min": 0.000260436646, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039065496899999995, "min": 0.0039065496899999995, "max": 0.12109304588, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009399845264852047, "min": 0.009399845264852047, "max": 0.3991324305534363, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14099767804145813, "min": 0.14099767804145813, "max": 2.793926954269409, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.9268292682927, "min": 353.3658536585366, "max": 991.8235294117648, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31400.0, "min": 16861.0, "max": 32570.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4462829115005529, "min": -0.9257806960132814, "max": 1.5978414447205822, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.59519874304533, "min": -28.699201576411724, "max": 131.02299846708775, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4462829115005529, "min": -0.9257806960132814, "max": 1.5978414447205822, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.59519874304533, "min": -28.699201576411724, "max": 131.02299846708775, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037759377900085114, "min": 0.03697864875188892, "max": 7.650612707523739, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0962689878069796, "min": 3.0322491976548918, "max": 130.06041602790356, "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": "1743947718", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/mbailey91/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --torch-device cuda:0", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1743949552" }, "total": 1833.9800609539961, "count": 1, "self": 0.47291304101236165, "children": { "run_training.setup": { "total": 0.058387987955939025, "count": 1, "self": 0.058387987955939025 }, "TrainerController.start_learning": { "total": 1833.4487599250278, "count": 1, "self": 1.1401545439730398, "children": { "TrainerController._reset_env": { "total": 6.726384826994035, "count": 1, "self": 6.726384826994035 }, "TrainerController.advance": { "total": 1825.4007124880445, "count": 63670, "self": 1.1674656518734992, "children": { "env_step": { "total": 1117.888970472617, "count": 63670, "self": 892.2397801164188, "children": { "SubprocessEnvManager._take_step": { "total": 224.90528221195564, "count": 63670, "self": 3.30679844081169, "children": { "TorchPolicy.evaluate": { "total": 221.59848377114395, "count": 62552, "self": 221.59848377114395 } } }, "workers": { "total": 0.7439081442425959, "count": 63670, "self": 0.0, "children": { "worker_root": { "total": 1830.761465942196, "count": 63670, "is_parallel": true, "self": 1013.8731698257616, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016639860114082694, "count": 1, "is_parallel": true, "self": 0.0008127939654514194, "children": { "_process_rank_one_or_two_observation": { "total": 0.00085119204595685, "count": 8, "is_parallel": true, "self": 0.00085119204595685 } } }, "UnityEnvironment.step": { "total": 0.029436142009217292, "count": 1, "is_parallel": true, "self": 0.0002289959811605513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002390980371274054, "count": 1, "is_parallel": true, "self": 0.0002390980371274054 }, "communicator.exchange": { "total": 0.028324952989351004, "count": 1, "is_parallel": true, "self": 0.028324952989351004 }, "steps_from_proto": { "total": 0.000643095001578331, "count": 1, "is_parallel": true, "self": 0.00018729909788817167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004557959036901593, "count": 8, "is_parallel": true, "self": 0.0004557959036901593 } } } } } } }, "UnityEnvironment.step": { "total": 816.8882961164345, "count": 63669, "is_parallel": true, "self": 13.75191771495156, "children": { "UnityEnvironment._generate_step_input": { "total": 9.910800162993837, "count": 63669, "is_parallel": true, "self": 9.910800162993837 }, "communicator.exchange": { "total": 751.8878948152997, "count": 63669, "is_parallel": true, "self": 751.8878948152997 }, "steps_from_proto": { "total": 41.337683423189446, "count": 63669, "is_parallel": true, "self": 11.644103783008177, "children": { "_process_rank_one_or_two_observation": { "total": 29.69357964018127, "count": 509352, "is_parallel": true, "self": 29.69357964018127 } } } } } } } } } } }, "trainer_advance": { "total": 706.344276363554, "count": 63670, "self": 2.071348280122038, "children": { "process_trajectory": { "total": 117.92718750826316, "count": 63670, "self": 117.5984374662512, "children": { "RLTrainer._checkpoint": { "total": 0.32875004201196134, "count": 2, "self": 0.32875004201196134 } } }, "_update_policy": { "total": 586.3457405751687, "count": 455, "self": 255.5768202964682, "children": { "TorchPPOOptimizer.update": { "total": 330.76892027870053, "count": 22764, "self": 330.76892027870053 } } } } } } }, "trainer_threads": { "total": 6.00004568696022e-07, "count": 1, "self": 6.00004568696022e-07 }, "TrainerController._save_models": { "total": 0.18150746601168066, "count": 1, "self": 0.03947994497139007, "children": { "RLTrainer._checkpoint": { "total": 0.1420275210402906, "count": 1, "self": 0.1420275210402906 } } } } } } }