{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3243020474910736, "min": 0.3188101053237915, "max": 1.40115487575531, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9775.7607421875, "min": 9573.029296875, "max": 42505.43359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02190645970404148, "min": -0.11521469801664352, "max": -0.011537670157849789, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -5.323269844055176, "min": -27.305883407592773, "max": -2.792116165161133, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07208328694105148, "min": 0.05745426565408707, "max": 0.5503643155097961, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 17.516239166259766, "min": 13.903932571411133, "max": 130.43634033203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06754646803283976, "min": 0.06376328436399031, "max": 0.07532013945268555, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0131970204925964, "min": 0.5272409761687988, "max": 1.075024008186244, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.002521428739142792, "min": 0.000693264136255287, "max": 0.02201266024277639, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03782143108714188, "min": 0.009705697907574017, "max": 0.1540886216994347, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.491777502773335e-06, "min": 7.491777502773335e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011237666254160003, "min": 0.00011237666254160003, "max": 0.0036326800891066996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249722666666666, "min": 0.10249722666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374584, "min": 1.3886848, "max": 2.6173924000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025947294400000003, "min": 0.00025947294400000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038920941600000007, "min": 0.0038920941600000007, "max": 0.12110824067000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0707831159234047, "min": 0.060127802193164825, "max": 0.6725010275840759, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.0617467164993286, "min": 0.8417892456054688, "max": 4.707507133483887, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 917.40625, "min": 876.5714285714286, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29357.0, "min": 15984.0, "max": 33017.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5428750496357679, "min": -1.0000000521540642, "max": -0.40947746533539986, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -17.372001588344574, "min": -29.84820169955492, "max": -12.693801425397396, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5428750496357679, "min": -1.0000000521540642, "max": -0.40947746533539986, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -17.372001588344574, "min": -29.84820169955492, "max": -12.693801425397396, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.6657587703957688, "min": 0.577468055493102, "max": 14.482045441865921, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 21.304280652664602, "min": 16.746573609299958, "max": 231.71272706985474, "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": "1750235602", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750238812" }, "total": 3209.519638939, "count": 1, "self": 0.6476430930001698, "children": { "run_training.setup": { "total": 0.04265654999994695, "count": 1, "self": 0.04265654999994695 }, "TrainerController.start_learning": { "total": 3208.829339296, "count": 1, "self": 2.299811721995411, "children": { "TrainerController._reset_env": { "total": 4.272367807999899, "count": 1, "self": 4.272367807999899 }, "TrainerController.advance": { "total": 3202.1823249760046, "count": 63236, "self": 2.8257812249530616, "children": { "env_step": { "total": 2112.232102758026, "count": 63236, "self": 1947.0636086950692, "children": { "SubprocessEnvManager._take_step": { "total": 163.7299610339751, "count": 63236, "self": 7.075567752945517, "children": { "TorchPolicy.evaluate": { "total": 156.65439328102957, "count": 62559, "self": 156.65439328102957 } } }, "workers": { "total": 1.4385330289817375, "count": 63236, "self": 0.0, "children": { "worker_root": { "total": 3199.4643864779155, "count": 63236, "is_parallel": true, "self": 1436.3143930818742, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006070991999990838, "count": 1, "is_parallel": true, "self": 0.004527722000034373, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015432699999564647, "count": 8, "is_parallel": true, "self": 0.0015432699999564647 } } }, "UnityEnvironment.step": { "total": 0.058658486000013, "count": 1, "is_parallel": true, "self": 0.0006472350000876759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005318920000263461, "count": 1, "is_parallel": true, "self": 0.0005318920000263461 }, "communicator.exchange": { "total": 0.055583624999940184, "count": 1, "is_parallel": true, "self": 0.055583624999940184 }, "steps_from_proto": { "total": 0.001895733999958793, "count": 1, "is_parallel": true, "self": 0.0004029819999686879, "children": { "_process_rank_one_or_two_observation": { "total": 0.001492751999990105, "count": 8, "is_parallel": true, "self": 0.001492751999990105 } } } } } } }, "UnityEnvironment.step": { "total": 1763.1499933960413, "count": 63235, "is_parallel": true, "self": 47.822565334064166, "children": { "UnityEnvironment._generate_step_input": { "total": 30.876029480998227, "count": 63235, "is_parallel": true, "self": 30.876029480998227 }, "communicator.exchange": { "total": 1555.6497297269643, "count": 63235, "is_parallel": true, "self": 1555.6497297269643 }, "steps_from_proto": { "total": 128.80166885401457, "count": 63235, "is_parallel": true, "self": 28.273736576210354, "children": { "_process_rank_one_or_two_observation": { "total": 100.52793227780421, "count": 505880, "is_parallel": true, "self": 100.52793227780421 } } } } } } } } } } }, "trainer_advance": { "total": 1087.1244409930255, "count": 63236, "self": 4.953728226041903, "children": { "process_trajectory": { "total": 165.6420338739805, "count": 63236, "self": 165.2829175589801, "children": { "RLTrainer._checkpoint": { "total": 0.3591163150003922, "count": 2, "self": 0.3591163150003922 } } }, "_update_policy": { "total": 916.5286788930031, "count": 454, "self": 377.75875097997016, "children": { "TorchPPOOptimizer.update": { "total": 538.7699279130329, "count": 22740, "self": 538.7699279130329 } } } } } } }, "trainer_threads": { "total": 1.0979993021464907e-06, "count": 1, "self": 1.0979993021464907e-06 }, "TrainerController._save_models": { "total": 0.07483369200053858, "count": 1, "self": 0.0019533600006980123, "children": { "RLTrainer._checkpoint": { "total": 0.07288033199984056, "count": 1, "self": 0.07288033199984056 } } } } } } }