{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39683642983436584, "min": 0.3928750157356262, "max": 1.4675036668777466, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11835.25, "min": 11835.25, "max": 44518.19140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5897131562232971, "min": -0.09040573984384537, "max": 0.66984623670578, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 166.29910278320312, "min": -21.697378158569336, "max": 192.91571044921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0012653418816626072, "min": -0.01722562499344349, "max": 0.2303726077079773, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.35682642459869385, "min": -4.8059492111206055, "max": 55.519798278808594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07149178699790161, "min": 0.06583988447391549, "max": 0.0742858538772684, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0008850179706226, "min": 0.5143103057962852, "max": 1.0802477465961902, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01706551619489411, "min": 0.0005108097153346259, "max": 0.017465132610774235, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23891722672851756, "min": 0.005618906868680886, "max": 0.24599706401932053, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.454326086685718e-06, "min": 7.454326086685718e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010436056521360005, "min": 0.00010436056521360005, "max": 0.0033805418731528, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248474285714286, "min": 0.10248474285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347864000000001, "min": 1.3886848, "max": 2.527710000000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002582258114285716, "min": 0.0002582258114285716, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036151613600000024, "min": 0.0036151613600000024, "max": 0.11271203528000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007738643325865269, "min": 0.007738643325865269, "max": 0.4328215420246124, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10834100842475891, "min": 0.10834100842475891, "max": 3.0297508239746094, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 311.61, "min": 277.0183486238532, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31161.0, "min": 15984.0, "max": 32779.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6469656342659333, "min": -1.0000000521540642, "max": 1.72212035636659, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.0495977923274, "min": -30.997401610016823, "max": 185.98899848759174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6469656342659333, "min": -1.0000000521540642, "max": 1.72212035636659, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.0495977923274, "min": -30.997401610016823, "max": 185.98899848759174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02485793294806052, "min": 0.023075643367239815, "max": 8.637586353346705, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4609353618579917, "min": 2.3624375510262325, "max": 138.2013816535473, "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": "1736268063", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=PyramidsTraining --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736270708" }, "total": 2644.7429433419998, "count": 1, "self": 0.9680932010001015, "children": { "run_training.setup": { "total": 0.0611510090000138, "count": 1, "self": 0.0611510090000138 }, "TrainerController.start_learning": { "total": 2643.713699132, "count": 1, "self": 1.9600675859774128, "children": { "TrainerController._reset_env": { "total": 6.391272173999994, "count": 1, "self": 6.391272173999994 }, "TrainerController.advance": { "total": 2635.215365804022, "count": 64140, "self": 1.969712547002473, "children": { "env_step": { "total": 1877.9813384169938, "count": 64140, "self": 1687.8067575290456, "children": { "SubprocessEnvManager._take_step": { "total": 189.00242469096472, "count": 64140, "self": 5.807337278982544, "children": { "TorchPolicy.evaluate": { "total": 183.19508741198217, "count": 62558, "self": 183.19508741198217 } } }, "workers": { "total": 1.1721561969833942, "count": 64140, "self": 0.0, "children": { "worker_root": { "total": 2636.979889072022, "count": 64140, "is_parallel": true, "self": 1099.6038553030262, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002299437999994325, "count": 1, "is_parallel": true, "self": 0.0007093689999635444, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015900690000307804, "count": 8, "is_parallel": true, "self": 0.0015900690000307804 } } }, "UnityEnvironment.step": { "total": 0.05736539199997992, "count": 1, "is_parallel": true, "self": 0.000805590999988226, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005277100000000701, "count": 1, "is_parallel": true, "self": 0.0005277100000000701 }, "communicator.exchange": { "total": 0.05374838299999851, "count": 1, "is_parallel": true, "self": 0.05374838299999851 }, "steps_from_proto": { "total": 0.002283707999993112, "count": 1, "is_parallel": true, "self": 0.0006034959999681178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016802120000249943, "count": 8, "is_parallel": true, "self": 0.0016802120000249943 } } } } } } }, "UnityEnvironment.step": { "total": 1537.376033768996, "count": 64139, "is_parallel": true, "self": 40.401838995957405, "children": { "UnityEnvironment._generate_step_input": { "total": 27.033825481048154, "count": 64139, "is_parallel": true, "self": 27.033825481048154 }, "communicator.exchange": { "total": 1352.773409651984, "count": 64139, "is_parallel": true, "self": 1352.773409651984 }, "steps_from_proto": { "total": 117.16695964000652, "count": 64139, "is_parallel": true, "self": 25.525550018082043, "children": { "_process_rank_one_or_two_observation": { "total": 91.64140962192448, "count": 513112, "is_parallel": true, "self": 91.64140962192448 } } } } } } } } } } }, "trainer_advance": { "total": 755.2643148400258, "count": 64140, "self": 3.74536719001037, "children": { "process_trajectory": { "total": 152.2606718050134, "count": 64140, "self": 151.89821834101312, "children": { "RLTrainer._checkpoint": { "total": 0.3624534640002821, "count": 2, "self": 0.3624534640002821 } } }, "_update_policy": { "total": 599.258275845002, "count": 455, "self": 335.59588270299594, "children": { "TorchPPOOptimizer.update": { "total": 263.66239314200607, "count": 22824, "self": 263.66239314200607 } } } } } } }, "trainer_threads": { "total": 1.6520002645847853e-06, "count": 1, "self": 1.6520002645847853e-06 }, "TrainerController._save_models": { "total": 0.1469919160003883, "count": 1, "self": 0.002363842000704608, "children": { "RLTrainer._checkpoint": { "total": 0.1446280739996837, "count": 1, "self": 0.1446280739996837 } } } } } } }