{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3810027241706848, "min": 0.3810027241706848, "max": 1.4327415227890015, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11259.392578125, "min": 11259.392578125, "max": 43463.6484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5958008170127869, "min": -0.2856314480304718, "max": 0.7400102615356445, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.29141235351562, "min": -67.69465637207031, "max": 198.32275390625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02725687250494957, "min": 0.026031309738755226, "max": 0.7800797820091248, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.19581413269043, "min": 6.71607780456543, "max": 184.87890625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06790267418462982, "min": 0.06736714873955969, "max": 0.07418762125765041, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9506374385848175, "min": 0.5110900348313314, "max": 1.058998348203022, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0105950219674144, "min": 0.00011257775114183562, "max": 0.011147382700015408, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1483303075438016, "min": 0.000900622009134685, "max": 0.15984516440067262, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.4537240403428558e-05, "min": 2.4537240403428558e-05, "max": 0.0009838354301878857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0003435213656479998, "min": 0.0003435213656479998, "max": 0.010020050197995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245371428571429, "min": 0.10245371428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434352, "min": 1.3691136000000002, "max": 2.4004248, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 1.2208342857142858e-05, "min": 1.2208342857142858e-05, "max": 9.854518857142857e-05, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00017091680000000002, "min": 0.00017091680000000002, "max": 0.00104038232, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012177111580967903, "min": 0.011694434098899364, "max": 0.35659000277519226, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17047956585884094, "min": 0.16372208297252655, "max": 2.4961299896240234, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 482.96666666666664, "min": 441.6764705882353, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28978.0, "min": 15984.0, "max": 33324.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.35520980617062, "min": -1.0000000521540642, "max": 1.4382806196808815, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 82.66779817640781, "min": -32.000001668930054, "max": 93.96219828724861, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.35520980617062, "min": -1.0000000521540642, "max": 1.4382806196808815, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 82.66779817640781, "min": -32.000001668930054, "max": 93.96219828724861, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06479253911997238, "min": 0.05611740758938728, "max": 9.845519872382283, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.952344886318315, "min": 3.5462809289165307, "max": 157.52831795811653, "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": "1746457361", "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 Training1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746459899" }, "total": 2537.458616328, "count": 1, "self": 0.47547662900069554, "children": { "run_training.setup": { "total": 0.020622181999897293, "count": 1, "self": 0.020622181999897293 }, "TrainerController.start_learning": { "total": 2536.9625175169995, "count": 1, "self": 1.3124354622286774, "children": { "TrainerController._reset_env": { "total": 2.219502709000153, "count": 1, "self": 2.219502709000153 }, "TrainerController.advance": { "total": 2533.3347599917715, "count": 63484, "self": 1.4098596733283557, "children": { "env_step": { "total": 1501.5122837727222, "count": 63484, "self": 1350.8759863185287, "children": { "SubprocessEnvManager._take_step": { "total": 149.85782354919138, "count": 63484, "self": 4.705159901363004, "children": { "TorchPolicy.evaluate": { "total": 145.15266364782838, "count": 62565, "self": 145.15266364782838 } } }, "workers": { "total": 0.7784739050021017, "count": 63484, "self": 0.0, "children": { "worker_root": { "total": 2532.0665197640374, "count": 63484, "is_parallel": true, "self": 1295.8601934498693, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022961549993851804, "count": 1, "is_parallel": true, "self": 0.0006994099985604407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015967450008247397, "count": 8, "is_parallel": true, "self": 0.0015967450008247397 } } }, "UnityEnvironment.step": { "total": 0.047689295999589376, "count": 1, "is_parallel": true, "self": 0.000533751000148186, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005162659999768948, "count": 1, "is_parallel": true, "self": 0.0005162659999768948 }, "communicator.exchange": { "total": 0.04507649199968, "count": 1, "is_parallel": true, "self": 0.04507649199968 }, "steps_from_proto": { "total": 0.0015627869997842936, "count": 1, "is_parallel": true, "self": 0.00033443399934185436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012283530004424392, "count": 8, "is_parallel": true, "self": 0.0012283530004424392 } } } } } } }, "UnityEnvironment.step": { "total": 1236.206326314168, "count": 63483, "is_parallel": true, "self": 31.635081907414133, "children": { "UnityEnvironment._generate_step_input": { "total": 23.60558687480807, "count": 63483, "is_parallel": true, "self": 23.60558687480807 }, "communicator.exchange": { "total": 1084.1305624629204, "count": 63483, "is_parallel": true, "self": 1084.1305624629204 }, "steps_from_proto": { "total": 96.83509506902556, "count": 63483, "is_parallel": true, "self": 19.54165666966037, "children": { "_process_rank_one_or_two_observation": { "total": 77.29343839936519, "count": 507864, "is_parallel": true, "self": 77.29343839936519 } } } } } } } } } } }, "trainer_advance": { "total": 1030.412616545721, "count": 63484, "self": 2.525724707905283, "children": { "process_trajectory": { "total": 128.39281419481722, "count": 63484, "self": 128.1965452408176, "children": { "RLTrainer._checkpoint": { "total": 0.1962689539996063, "count": 2, "self": 0.1962689539996063 } } }, "_update_policy": { "total": 899.4940776429985, "count": 433, "self": 498.0586412210314, "children": { "TorchPPOOptimizer.update": { "total": 401.4354364219671, "count": 38035, "self": 401.4354364219671 } } } } } } }, "trainer_threads": { "total": 9.079994924832135e-07, "count": 1, "self": 9.079994924832135e-07 }, "TrainerController._save_models": { "total": 0.09581844599961187, "count": 1, "self": 0.001811391000956064, "children": { "RLTrainer._checkpoint": { "total": 0.0940070549986558, "count": 1, "self": 0.0940070549986558 } } } } } } }