{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4013271927833557, "min": 0.4013271927833557, "max": 1.4670896530151367, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12059.0791015625, "min": 12059.0791015625, "max": 44505.6328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47065258026123047, "min": -0.1009935587644577, "max": 0.556468665599823, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.60554504394531, "min": -24.238454818725586, "max": 155.81121826171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04222549498081207, "min": 0.009586496278643608, "max": 0.3111784756183624, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.358657836914062, "min": 2.597940444946289, "max": 74.68283081054688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06706211439173092, "min": 0.06501416019524359, "max": 0.07382208878851218, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9388696014842329, "min": 0.5069299551551952, "max": 1.0790754478560605, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01516514645239416, "min": 0.00020106498791826882, "max": 0.016048707720805324, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21231205033351824, "min": 0.0026138448429374947, "max": 0.22468190809127453, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.618468889114288e-06, "min": 7.618468889114288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010665856444760002, "min": 0.00010665856444760002, "max": 0.0032254453248516, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253945714285717, "min": 0.10253945714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355524000000004, "min": 1.3691136000000002, "max": 2.4429893000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002636917685714286, "min": 0.0002636917685714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036916847600000006, "min": 0.0036916847600000006, "max": 0.10752732516, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012817338109016418, "min": 0.012794054113328457, "max": 0.46144887804985046, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17944273352622986, "min": 0.17911675572395325, "max": 3.230142116546631, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 393.8831168831169, "min": 335.4470588235294, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30329.0, "min": 15984.0, "max": 33263.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5021947798403827, "min": -1.0000000521540642, "max": 1.6439139380357985, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.66899804770947, "min": -32.000001668930054, "max": 146.36499825119972, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5021947798403827, "min": -1.0000000521540642, "max": 1.6439139380357985, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.66899804770947, "min": -32.000001668930054, "max": 146.36499825119972, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05164418501217015, "min": 0.04612435837280341, "max": 8.744253631681204, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9766022459371015, "min": 3.966694820061093, "max": 139.90805810689926, "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": "1764134613", "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_v1 --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": "1764137011" }, "total": 2398.0228086380002, "count": 1, "self": 0.58302697200088, "children": { "run_training.setup": { "total": 0.04779733500004113, "count": 1, "self": 0.04779733500004113 }, "TrainerController.start_learning": { "total": 2397.3919843309995, "count": 1, "self": 1.4120243560000745, "children": { "TrainerController._reset_env": { "total": 4.790785185000004, "count": 1, "self": 4.790785185000004 }, "TrainerController.advance": { "total": 2391.045562572999, "count": 63769, "self": 1.5521252090502458, "children": { "env_step": { "total": 1688.440378658967, "count": 63769, "self": 1526.4749189050349, "children": { "SubprocessEnvManager._take_step": { "total": 161.05888412292688, "count": 63769, "self": 5.105903281006022, "children": { "TorchPolicy.evaluate": { "total": 155.95298084192086, "count": 62559, "self": 155.95298084192086 } } }, "workers": { "total": 0.9065756310051256, "count": 63769, "self": 0.0, "children": { "worker_root": { "total": 2389.1477721319834, "count": 63769, "is_parallel": true, "self": 992.0827429029484, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020974760000171955, "count": 1, "is_parallel": true, "self": 0.0006948459999875922, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014026300000296033, "count": 8, "is_parallel": true, "self": 0.0014026300000296033 } } }, "UnityEnvironment.step": { "total": 0.05403799800001252, "count": 1, "is_parallel": true, "self": 0.0005592589998286712, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004965109999375272, "count": 1, "is_parallel": true, "self": 0.0004965109999375272 }, "communicator.exchange": { "total": 0.051250353000114046, "count": 1, "is_parallel": true, "self": 0.051250353000114046 }, "steps_from_proto": { "total": 0.001731875000132277, "count": 1, "is_parallel": true, "self": 0.0003486710004381166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013832039996941603, "count": 8, "is_parallel": true, "self": 0.0013832039996941603 } } } } } } }, "UnityEnvironment.step": { "total": 1397.065029229035, "count": 63768, "is_parallel": true, "self": 36.34709157999828, "children": { "UnityEnvironment._generate_step_input": { "total": 24.82950759502205, "count": 63768, "is_parallel": true, "self": 24.82950759502205 }, "communicator.exchange": { "total": 1214.6476851700522, "count": 63768, "is_parallel": true, "self": 1214.6476851700522 }, "steps_from_proto": { "total": 121.2407448839624, "count": 63768, "is_parallel": true, "self": 25.42391958884309, "children": { "_process_rank_one_or_two_observation": { "total": 95.81682529511932, "count": 510144, "is_parallel": true, "self": 95.81682529511932 } } } } } } } } } } }, "trainer_advance": { "total": 701.0530587049818, "count": 63769, "self": 2.698205400919278, "children": { "process_trajectory": { "total": 138.5313799970645, "count": 63769, "self": 138.22730650506492, "children": { "RLTrainer._checkpoint": { "total": 0.30407349199958844, "count": 2, "self": 0.30407349199958844 } } }, "_update_policy": { "total": 559.823473306998, "count": 442, "self": 312.9236916470172, "children": { "TorchPPOOptimizer.update": { "total": 246.89978165998082, "count": 22815, "self": 246.89978165998082 } } } } } } }, "trainer_threads": { "total": 1.0960002327919938e-06, "count": 1, "self": 1.0960002327919938e-06 }, "TrainerController._save_models": { "total": 0.14361112100004902, "count": 1, "self": 0.014733793000232254, "children": { "RLTrainer._checkpoint": { "total": 0.12887732799981677, "count": 1, "self": 0.12887732799981677 } } } } } } }