{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3323443830013275, "min": 0.3323443830013275, "max": 0.9277193546295166, "count": 25 }, "Pyramids.Policy.Entropy.sum": { "value": 9848.0283203125, "min": 9848.0283203125, "max": 27401.119140625, "count": 25 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 269987.0, "max": 989993.0, "count": 25 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 269987.0, "max": 989993.0, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5659830570220947, "min": 0.0358235202729702, "max": 0.6446145176887512, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.47525024414062, "min": 3.940587282180786, "max": 183.07052612304688, "count": 25 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012129790149629116, "min": 0.003952191676944494, "max": 0.06148092821240425, "count": 25 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.396341323852539, "min": 1.098709225654602, "max": 11.747032165527344, "count": 25 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06921870409719512, "min": 0.06513417597161605, "max": 0.07468809912888418, "count": 25 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0382805614579267, "min": 0.35910715823411005, "max": 1.0456333878043784, "count": 25 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017415203904566426, "min": 0.004488226002461231, "max": 0.017415203904566426, "count": 25 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2612280585684964, "min": 0.027312128574218757, "max": 0.2612280585684964, "count": 25 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2518730829606664e-05, "min": 1.2518730829606664e-05, "max": 0.00036770342645932005, "count": 25 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00018778096244409994, "min": 0.00018778096244409994, "max": 0.004912830517433998, "count": 25 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250372666666667, "min": 0.10250372666666667, "max": 0.17354068, "count": 25 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375559, "min": 0.8677034, "max": 2.4825660000000003, "count": 25 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002601222939999999, "min": 0.0002601222939999999, "max": 0.007356713932000001, "count": 25 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039018344099999987, "min": 0.0039018344099999987, "max": 0.09830834340000001, "count": 25 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01728876680135727, "min": 0.017119331285357475, "max": 0.05122077465057373, "count": 25 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.25933149456977844, "min": 0.23967064917087555, "max": 0.5879389047622681, "count": 25 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 318.4891304347826, "min": 305.6458333333333, "max": 840.8048780487804, "count": 25 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29301.0, "min": 2836.0, "max": 34473.0, "count": 25 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5727804158206866, "min": -0.20727321650923752, "max": 1.6943541465637584, "count": 25 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.69579825550318, "min": -8.498201876878738, "max": 162.6579980701208, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5727804158206866, "min": -0.20727321650923752, "max": 1.6943541465637584, "count": 25 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.69579825550318, "min": -8.498201876878738, "max": 162.6579980701208, "count": 25 }, "Pyramids.Policy.RndReward.mean": { "value": 0.057363812205079266, "min": 0.054105166086173995, "max": 0.40900284373882884, "count": 25 }, "Pyramids.Policy.RndReward.sum": { "value": 5.277470722867292, "min": 1.527510574203916, "max": 16.769116593291983, "count": 25 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717229904", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717231682" }, "total": 1778.106262463, "count": 1, "self": 0.4772313909998047, "children": { "run_training.setup": { "total": 0.05048857100018722, "count": 1, "self": 0.05048857100018722 }, "TrainerController.start_learning": { "total": 1777.578542501, "count": 1, "self": 1.045551888979844, "children": { "TrainerController._reset_env": { "total": 2.209144826999818, "count": 1, "self": 2.209144826999818 }, "TrainerController.advance": { "total": 1774.2354642020205, "count": 47767, "self": 1.085495056003765, "children": { "env_step": { "total": 1298.841299062075, "count": 47767, "self": 1195.74789817101, "children": { "SubprocessEnvManager._take_step": { "total": 102.45932746504513, "count": 47767, "self": 3.6522131160336357, "children": { "TorchPolicy.evaluate": { "total": 98.8071143490115, "count": 46548, "self": 98.8071143490115 } } }, "workers": { "total": 0.6340734260197678, "count": 47767, "self": 0.0, "children": { "worker_root": { "total": 1773.5019123530228, "count": 47767, "is_parallel": true, "self": 673.5860124210171, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002153898999949888, "count": 1, "is_parallel": true, "self": 0.0006879729994579975, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014659260004918906, "count": 8, "is_parallel": true, "self": 0.0014659260004918906 } } }, "UnityEnvironment.step": { "total": 0.05119979799974317, "count": 1, "is_parallel": true, "self": 0.001861483000084263, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005347289998098859, "count": 1, "is_parallel": true, "self": 0.0005347289998098859 }, "communicator.exchange": { "total": 0.04693047299997488, "count": 1, "is_parallel": true, "self": 0.04693047299997488 }, "steps_from_proto": { "total": 0.001873112999874138, "count": 1, "is_parallel": true, "self": 0.0003845750006803428, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014885379991937953, "count": 8, "is_parallel": true, "self": 0.0014885379991937953 } } } } } } }, "UnityEnvironment.step": { "total": 1099.9158999320057, "count": 47766, "is_parallel": true, "self": 25.599184794084522, "children": { "UnityEnvironment._generate_step_input": { "total": 18.547018886950354, "count": 47766, "is_parallel": true, "self": 18.547018886950354 }, "communicator.exchange": { "total": 978.4382137229713, "count": 47766, "is_parallel": true, "self": 978.4382137229713 }, "steps_from_proto": { "total": 77.33148252799947, "count": 47766, "is_parallel": true, "self": 15.922522607053452, "children": { "_process_rank_one_or_two_observation": { "total": 61.40895992094602, "count": 382128, "is_parallel": true, "self": 61.40895992094602 } } } } } } } } } } }, "trainer_advance": { "total": 474.3086700839417, "count": 47767, "self": 2.056256513886183, "children": { "process_trajectory": { "total": 99.73064170805173, "count": 47767, "self": 99.51213664805164, "children": { "RLTrainer._checkpoint": { "total": 0.21850506000009773, "count": 2, "self": 0.21850506000009773 } } }, "_update_policy": { "total": 372.5217718620038, "count": 349, "self": 219.09414086200786, "children": { "TorchPPOOptimizer.update": { "total": 153.42763099999593, "count": 16911, "self": 153.42763099999593 } } } } } } }, "trainer_threads": { "total": 1.1729998732334934e-06, "count": 1, "self": 1.1729998732334934e-06 }, "TrainerController._save_models": { "total": 0.08838040999989971, "count": 1, "self": 0.0017367949999425036, "children": { "RLTrainer._checkpoint": { "total": 0.08664361499995721, "count": 1, "self": 0.08664361499995721 } } } } } } }