{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.430239200592041, "min": 0.40906527638435364, "max": 1.4678257703781128, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12810.802734375, "min": 12147.6025390625, "max": 44527.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4376915693283081, "min": -0.08460094034671783, "max": 0.5268000364303589, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.30133819580078, "min": -20.388826370239258, "max": 145.3968048095703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0379365012049675, "min": -0.02386993169784546, "max": 0.31540539860725403, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.166982650756836, "min": -6.301661968231201, "max": 76.01270294189453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06741595966513178, "min": 0.0641823230781549, "max": 0.07525428700995249, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9438234353118449, "min": 0.5267800090696674, "max": 1.0859606982403958, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014488492045751351, "min": 0.0008473686268708609, "max": 0.015833051600826105, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2028388886405189, "min": 0.011863160776192053, "max": 0.22166272241156548, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6064260359857145e-06, "min": 7.6064260359857145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001064899645038, "min": 0.0001064899645038, "max": 0.0035083856305382, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253544285714286, "min": 0.10253544285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354962, "min": 1.3886848, "max": 2.5694617999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002632907414285715, "min": 0.0002632907414285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003686070380000001, "min": 0.003686070380000001, "max": 0.11696923382, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008851827122271061, "min": 0.008851827122271061, "max": 0.5529447793960571, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1239255741238594, "min": 0.1239255741238594, "max": 3.8706133365631104, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 389.69135802469134, "min": 377.36708860759495, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31565.0, "min": 15984.0, "max": 32857.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.462108623282409, "min": -1.0000000521540642, "max": 1.5218826428055763, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.43079848587513, "min": -28.88740162551403, "max": 123.71079806238413, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.462108623282409, "min": -1.0000000521540642, "max": 1.5218826428055763, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.43079848587513, "min": -28.88740162551403, "max": 123.71079806238413, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0357987076670354, "min": 0.0357987076670354, "max": 11.130412332713604, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.899695321029867, "min": 2.747842547003529, "max": 178.08659732341766, "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": "1703754280", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703756494" }, "total": 2214.2559791050003, "count": 1, "self": 0.4774131810004292, "children": { "run_training.setup": { "total": 0.046206724000057875, "count": 1, "self": 0.046206724000057875 }, "TrainerController.start_learning": { "total": 2213.7323592, "count": 1, "self": 1.3860725880249447, "children": { "TrainerController._reset_env": { "total": 2.1009759710000253, "count": 1, "self": 2.1009759710000253 }, "TrainerController.advance": { "total": 2210.1591699469745, "count": 63775, "self": 1.3948652759713696, "children": { "env_step": { "total": 1574.890967365047, "count": 63775, "self": 1446.1095274479771, "children": { "SubprocessEnvManager._take_step": { "total": 127.9323430929494, "count": 63775, "self": 4.6978946979861576, "children": { "TorchPolicy.evaluate": { "total": 123.23444839496324, "count": 62566, "self": 123.23444839496324 } } }, "workers": { "total": 0.8490968241203518, "count": 63775, "self": 0.0, "children": { "worker_root": { "total": 2208.503645399029, "count": 63775, "is_parallel": true, "self": 880.6934897659926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001732272000026569, "count": 1, "is_parallel": true, "self": 0.0005307340011313499, "children": { "_process_rank_one_or_two_observation": { "total": 0.001201537998895219, "count": 8, "is_parallel": true, "self": 0.001201537998895219 } } }, "UnityEnvironment.step": { "total": 0.049091842000052566, "count": 1, "is_parallel": true, "self": 0.0006434359997911088, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005127819999870553, "count": 1, "is_parallel": true, "self": 0.0005127819999870553 }, "communicator.exchange": { "total": 0.04631333599991194, "count": 1, "is_parallel": true, "self": 0.04631333599991194 }, "steps_from_proto": { "total": 0.0016222880003624596, "count": 1, "is_parallel": true, "self": 0.0003510529995764955, "children": { "_process_rank_one_or_two_observation": { "total": 0.001271235000785964, "count": 8, "is_parallel": true, "self": 0.001271235000785964 } } } } } } }, "UnityEnvironment.step": { "total": 1327.8101556330366, "count": 63774, "is_parallel": true, "self": 34.68636431999312, "children": { "UnityEnvironment._generate_step_input": { "total": 23.67535175403009, "count": 63774, "is_parallel": true, "self": 23.67535175403009 }, "communicator.exchange": { "total": 1171.7564905050044, "count": 63774, "is_parallel": true, "self": 1171.7564905050044 }, "steps_from_proto": { "total": 97.691949054009, "count": 63774, "is_parallel": true, "self": 19.74798513017049, "children": { "_process_rank_one_or_two_observation": { "total": 77.94396392383851, "count": 510192, "is_parallel": true, "self": 77.94396392383851 } } } } } } } } } } }, "trainer_advance": { "total": 633.8733373059563, "count": 63775, "self": 2.7152273039523607, "children": { "process_trajectory": { "total": 124.78068506800537, "count": 63775, "self": 124.59194246700508, "children": { "RLTrainer._checkpoint": { "total": 0.1887426010002855, "count": 2, "self": 0.1887426010002855 } } }, "_update_policy": { "total": 506.37742493399855, "count": 454, "self": 301.2270654810163, "children": { "TorchPPOOptimizer.update": { "total": 205.15035945298223, "count": 22800, "self": 205.15035945298223 } } } } } } }, "trainer_threads": { "total": 8.160004654200748e-07, "count": 1, "self": 8.160004654200748e-07 }, "TrainerController._save_models": { "total": 0.0861398779998126, "count": 1, "self": 0.0014748679996046121, "children": { "RLTrainer._checkpoint": { "total": 0.08466501000020799, "count": 1, "self": 0.08466501000020799 } } } } } } }