{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39097166061401367, "min": 0.39097166061401367, "max": 1.4326444864273071, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11841.75, "min": 11695.240234375, "max": 43460.703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6403189897537231, "min": -0.1667199432849884, "max": 0.6403189897537231, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 181.21026611328125, "min": -39.51262664794922, "max": 181.21026611328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011348869651556015, "min": -0.01969035528600216, "max": 0.3381563425064087, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2117300033569336, "min": -5.021040439605713, "max": 80.14305114746094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06880426084583936, "min": 0.06602099334261202, "max": 0.07204867108148315, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0320639126875903, "min": 0.49542927702245887, "max": 1.0592615787286823, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016290232432691162, "min": 0.00044715984124048047, "max": 0.017264449444064186, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24435348649036742, "min": 0.006260237777366727, "max": 0.24435348649036742, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.570977476373333e-06, "min": 7.570977476373333e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001135646621456, "min": 0.0001135646621456, "max": 0.003509074130308699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252362666666667, "min": 0.10252362666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378544, "min": 1.3691136000000002, "max": 2.5696913, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000262110304, "min": 0.000262110304, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00393165456, "min": 0.00393165456, "max": 0.11699216087000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00832540076225996, "min": 0.008207755163311958, "max": 0.3344776928424835, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12488101422786713, "min": 0.11490856856107712, "max": 2.341343879699707, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.02912621359224, "min": 295.15533980582524, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30800.0, "min": 15984.0, "max": 33028.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6621262001470454, "min": -1.0000000521540642, "max": 1.6659922175181723, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.19899861514568, "min": -32.000001668930054, "max": 171.59719840437174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6621262001470454, "min": -1.0000000521540642, "max": 1.6659922175181723, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.19899861514568, "min": -32.000001668930054, "max": 171.59719840437174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02573409063223912, "min": 0.02573409063223912, "max": 6.5260189566761255, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6506113351206295, "min": 2.5975699304253794, "max": 104.41630330681801, "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": "1691714236", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691716567" }, "total": 2331.2847599140005, "count": 1, "self": 1.041851969000163, "children": { "run_training.setup": { "total": 0.03962273999991339, "count": 1, "self": 0.03962273999991339 }, "TrainerController.start_learning": { "total": 2330.2032852050006, "count": 1, "self": 1.4623620030674829, "children": { "TrainerController._reset_env": { "total": 5.479988999999932, "count": 1, "self": 5.479988999999932 }, "TrainerController.advance": { "total": 2323.113378192934, "count": 64020, "self": 1.5106463309025457, "children": { "env_step": { "total": 1633.6768066770383, "count": 64020, "self": 1520.8383699559447, "children": { "SubprocessEnvManager._take_step": { "total": 111.97414155901038, "count": 64020, "self": 4.735934557027576, "children": { "TorchPolicy.evaluate": { "total": 107.2382070019828, "count": 62545, "self": 107.2382070019828 } } }, "workers": { "total": 0.8642951620831809, "count": 64020, "self": 0.0, "children": { "worker_root": { "total": 2324.7955204649843, "count": 64020, "is_parallel": true, "self": 921.1916012870058, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002536320000217529, "count": 1, "is_parallel": true, "self": 0.0006544589996337891, "children": { "_process_rank_one_or_two_observation": { "total": 0.00188186100058374, "count": 8, "is_parallel": true, "self": 0.00188186100058374 } } }, "UnityEnvironment.step": { "total": 0.047729962999937925, "count": 1, "is_parallel": true, "self": 0.000592090999816719, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005110189999868453, "count": 1, "is_parallel": true, "self": 0.0005110189999868453 }, "communicator.exchange": { "total": 0.044695340000089345, "count": 1, "is_parallel": true, "self": 0.044695340000089345 }, "steps_from_proto": { "total": 0.0019315130000450154, "count": 1, "is_parallel": true, "self": 0.00037341100005505723, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015581019999899581, "count": 8, "is_parallel": true, "self": 0.0015581019999899581 } } } } } } }, "UnityEnvironment.step": { "total": 1403.6039191779785, "count": 64019, "is_parallel": true, "self": 34.38853562699978, "children": { "UnityEnvironment._generate_step_input": { "total": 23.35862423399385, "count": 64019, "is_parallel": true, "self": 23.35862423399385 }, "communicator.exchange": { "total": 1239.293995746001, "count": 64019, "is_parallel": true, "self": 1239.293995746001 }, "steps_from_proto": { "total": 106.56276357098386, "count": 64019, "is_parallel": true, "self": 20.869480681042205, "children": { "_process_rank_one_or_two_observation": { "total": 85.69328288994166, "count": 512152, "is_parallel": true, "self": 85.69328288994166 } } } } } } } } } } }, "trainer_advance": { "total": 687.925925184993, "count": 64020, "self": 2.659672714064527, "children": { "process_trajectory": { "total": 113.09464460893582, "count": 64020, "self": 112.79854820893502, "children": { "RLTrainer._checkpoint": { "total": 0.29609640000080617, "count": 2, "self": 0.29609640000080617 } } }, "_update_policy": { "total": 572.1716078619927, "count": 453, "self": 374.46103158794153, "children": { "TorchPPOOptimizer.update": { "total": 197.71057627405116, "count": 22854, "self": 197.71057627405116 } } } } } } }, "trainer_threads": { "total": 1.0759995348053053e-06, "count": 1, "self": 1.0759995348053053e-06 }, "TrainerController._save_models": { "total": 0.14755493299981026, "count": 1, "self": 0.001997058999222645, "children": { "RLTrainer._checkpoint": { "total": 0.14555787400058762, "count": 1, "self": 0.14555787400058762 } } } } } } }