{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5138388872146606, "min": 0.5080400705337524, "max": 1.498448371887207, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15374.0595703125, "min": 15363.130859375, "max": 45456.9296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6157060265541077, "min": -0.21406716108322144, "max": 0.6157060265541077, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.0919189453125, "min": -50.733917236328125, "max": 176.0919189453125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02693929150700569, "min": -0.039169225841760635, "max": 0.28814807534217834, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.70463752746582, "min": -10.771536827087402, "max": 68.29109191894531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06573178802629828, "min": 0.0651419756287, "max": 0.0726410480053425, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9859768203944743, "min": 0.47899956920019604, "max": 1.0541034531391538, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014932036686999103, "min": 0.0013503387780880035, "max": 0.01563697836224622, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22398055030498654, "min": 0.018384462603620557, "max": 0.22398055030498654, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5474574842133325e-06, "min": 7.5474574842133325e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011321186226319999, "min": 0.00011321186226319999, "max": 0.0037570780476406996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251578666666668, "min": 0.10251578666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377368000000002, "min": 1.3886848, "max": 2.6523593, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000261327088, "min": 0.000261327088, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039199063199999995, "min": 0.0039199063199999995, "max": 0.12525069407000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008436107076704502, "min": 0.008436107076704502, "max": 0.3440583348274231, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1265415996313095, "min": 0.12067276239395142, "max": 2.4084084033966064, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.36082474226805, "min": 292.36082474226805, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28359.0, "min": 15984.0, "max": 33171.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.687012352279781, "min": -1.0000000521540642, "max": 1.687012352279781, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.64019817113876, "min": -26.349801689386368, "max": 163.64019817113876, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.687012352279781, "min": -1.0000000521540642, "max": 1.687012352279781, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.64019817113876, "min": -26.349801689386368, "max": 163.64019817113876, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025669250699100997, "min": 0.025669250699100997, "max": 7.308761367574334, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4899173178127967, "min": 2.4899173178127967, "max": 116.94018188118935, "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": "1776777489", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py /content/ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1776779729" }, "total": 2239.631921993, "count": 1, "self": 0.47799708600041413, "children": { "run_training.setup": { "total": 0.024718357999972795, "count": 1, "self": 0.024718357999972795 }, "TrainerController.start_learning": { "total": 2239.1292065489997, "count": 1, "self": 1.4566781090379664, "children": { "TrainerController._reset_env": { "total": 2.1446335840000756, "count": 1, "self": 2.1446335840000756 }, "TrainerController.advance": { "total": 2235.4536270339613, "count": 63854, "self": 1.448912584923164, "children": { "env_step": { "total": 1570.2896358880334, "count": 63854, "self": 1414.1509219100699, "children": { "SubprocessEnvManager._take_step": { "total": 155.2708833519864, "count": 63854, "self": 4.8566258990331335, "children": { "TorchPolicy.evaluate": { "total": 150.41425745295328, "count": 62563, "self": 150.41425745295328 } } }, "workers": { "total": 0.8678306259771489, "count": 63854, "self": 0.0, "children": { "worker_root": { "total": 2232.7652033850272, "count": 63854, "is_parallel": true, "self": 939.3746803030263, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018444190000082017, "count": 1, "is_parallel": true, "self": 0.0006057980008336017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012386209991746, "count": 8, "is_parallel": true, "self": 0.0012386209991746 } } }, "UnityEnvironment.step": { "total": 0.05265335200010668, "count": 1, "is_parallel": true, "self": 0.0005881489996681921, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005069220001132635, "count": 1, "is_parallel": true, "self": 0.0005069220001132635 }, "communicator.exchange": { "total": 0.049725902000318456, "count": 1, "is_parallel": true, "self": 0.049725902000318456 }, "steps_from_proto": { "total": 0.0018323790000067675, "count": 1, "is_parallel": true, "self": 0.0003751910003302328, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014571879996765347, "count": 8, "is_parallel": true, "self": 0.0014571879996765347 } } } } } } }, "UnityEnvironment.step": { "total": 1293.390523082001, "count": 63853, "is_parallel": true, "self": 34.60886772517006, "children": { "UnityEnvironment._generate_step_input": { "total": 24.086681259973375, "count": 63853, "is_parallel": true, "self": 24.086681259973375 }, "communicator.exchange": { "total": 1122.433297434979, "count": 63853, "is_parallel": true, "self": 1122.433297434979 }, "steps_from_proto": { "total": 112.26167666187848, "count": 63853, "is_parallel": true, "self": 23.733901589077504, "children": { "_process_rank_one_or_two_observation": { "total": 88.52777507280098, "count": 510824, "is_parallel": true, "self": 88.52777507280098 } } } } } } } } } } }, "trainer_advance": { "total": 663.7150785610047, "count": 63854, "self": 2.9095772220498475, "children": { "process_trajectory": { "total": 129.37842630596015, "count": 63854, "self": 129.17778429196142, "children": { "RLTrainer._checkpoint": { "total": 0.20064201399873127, "count": 2, "self": 0.20064201399873127 } } }, "_update_policy": { "total": 531.4270750329947, "count": 458, "self": 292.14681188202894, "children": { "TorchPPOOptimizer.update": { "total": 239.28026315096577, "count": 22761, "self": 239.28026315096577 } } } } } } }, "trainer_threads": { "total": 9.390005288878456e-07, "count": 1, "self": 9.390005288878456e-07 }, "TrainerController._save_models": { "total": 0.07426688299983653, "count": 1, "self": 0.0010197789997619111, "children": { "RLTrainer._checkpoint": { "total": 0.07324710400007461, "count": 1, "self": 0.07324710400007461 } } } } } } }