{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4992523491382599, "min": 0.4992523491382599, "max": 1.4368122816085815, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14977.5703125, "min": 14977.5703125, "max": 43587.13671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4695327877998352, "min": -0.10257785767316818, "max": 0.4695327877998352, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.77384948730469, "min": -24.721263885498047, "max": 126.77384948730469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00361551227979362, "min": -0.00361551227979362, "max": 0.2599310576915741, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.9761883020401001, "min": -0.9761883020401001, "max": 62.38345718383789, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06565213015111272, "min": 0.06459844327487406, "max": 0.07325088515792441, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9191298221155781, "min": 0.5001573439937717, "max": 1.0789947755530356, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013295434062364766, "min": 0.0002453176367023755, "max": 0.013295434062364766, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18613607687310674, "min": 0.003189129277130882, "max": 0.18613607687310674, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.606061750392858e-06, "min": 7.606061750392858e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010648486450550002, "min": 0.00010648486450550002, "max": 0.0032527097157634996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253532142857144, "min": 0.10253532142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354945000000001, "min": 1.3886848, "max": 2.4436013999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002632786107142858, "min": 0.0002632786107142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036859005500000015, "min": 0.0036859005500000015, "max": 0.10844522635, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010151459835469723, "min": 0.009942200966179371, "max": 0.4211326241493225, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14212043583393097, "min": 0.13919080793857574, "max": 2.9479284286499023, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 391.97297297297297, "min": 391.97297297297297, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29006.0, "min": 15984.0, "max": 33631.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5269270047948167, "min": -1.0000000521540642, "max": 1.5269270047948167, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.99259835481644, "min": -31.999601677060127, "max": 112.99259835481644, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5269270047948167, "min": -1.0000000521540642, "max": 1.5269270047948167, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.99259835481644, "min": -31.999601677060127, "max": 112.99259835481644, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04090656361753448, "min": 0.04090656361753448, "max": 8.10820494685322, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0270857076975517, "min": 2.854461886920035, "max": 129.73127914965153, "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": "1693660006", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693662266" }, "total": 2260.477208345, "count": 1, "self": 0.5375704119996954, "children": { "run_training.setup": { "total": 0.04846043599997074, "count": 1, "self": 0.04846043599997074 }, "TrainerController.start_learning": { "total": 2259.891177497, "count": 1, "self": 1.6183679250257228, "children": { "TrainerController._reset_env": { "total": 4.312574903000041, "count": 1, "self": 4.312574903000041 }, "TrainerController.advance": { "total": 2253.856821898975, "count": 63540, "self": 1.645623145972877, "children": { "env_step": { "total": 1580.7124387809886, "count": 63540, "self": 1459.5707891489892, "children": { "SubprocessEnvManager._take_step": { "total": 120.14064883898482, "count": 63540, "self": 5.051337129938929, "children": { "TorchPolicy.evaluate": { "total": 115.08931170904589, "count": 62561, "self": 115.08931170904589 } } }, "workers": { "total": 1.001000793014498, "count": 63540, "self": 0.0, "children": { "worker_root": { "total": 2254.41834098898, "count": 63540, "is_parallel": true, "self": 920.5158193690017, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0048293419999936305, "count": 1, "is_parallel": true, "self": 0.003384422999886283, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014449190001073475, "count": 8, "is_parallel": true, "self": 0.0014449190001073475 } } }, "UnityEnvironment.step": { "total": 0.046218334000002415, "count": 1, "is_parallel": true, "self": 0.0006432119999431052, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000472922000028575, "count": 1, "is_parallel": true, "self": 0.000472922000028575 }, "communicator.exchange": { "total": 0.043152355000017906, "count": 1, "is_parallel": true, "self": 0.043152355000017906 }, "steps_from_proto": { "total": 0.0019498450000128287, "count": 1, "is_parallel": true, "self": 0.0003827550000323754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015670899999804533, "count": 8, "is_parallel": true, "self": 0.0015670899999804533 } } } } } } }, "UnityEnvironment.step": { "total": 1333.9025216199784, "count": 63539, "is_parallel": true, "self": 35.86950667289943, "children": { "UnityEnvironment._generate_step_input": { "total": 23.846895921035525, "count": 63539, "is_parallel": true, "self": 23.846895921035525 }, "communicator.exchange": { "total": 1165.5948715730358, "count": 63539, "is_parallel": true, "self": 1165.5948715730358 }, "steps_from_proto": { "total": 108.59124745300761, "count": 63539, "is_parallel": true, "self": 21.767169268011628, "children": { "_process_rank_one_or_two_observation": { "total": 86.82407818499598, "count": 508312, "is_parallel": true, "self": 86.82407818499598 } } } } } } } } } } }, "trainer_advance": { "total": 671.4987599720133, "count": 63540, "self": 3.057386330019085, "children": { "process_trajectory": { "total": 112.76556404499348, "count": 63540, "self": 112.5598744439938, "children": { "RLTrainer._checkpoint": { "total": 0.20568960099967626, "count": 2, "self": 0.20568960099967626 } } }, "_update_policy": { "total": 555.6758095970008, "count": 447, "self": 363.09138487597755, "children": { "TorchPPOOptimizer.update": { "total": 192.58442472102325, "count": 22791, "self": 192.58442472102325 } } } } } } }, "trainer_threads": { "total": 1.2579998838191386e-06, "count": 1, "self": 1.2579998838191386e-06 }, "TrainerController._save_models": { "total": 0.1034115119996386, "count": 1, "self": 0.0014972879998822464, "children": { "RLTrainer._checkpoint": { "total": 0.10191422399975636, "count": 1, "self": 0.10191422399975636 } } } } } } }