{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4822847247123718, "min": 0.4822847247123718, "max": 1.4362549781799316, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14391.3759765625, "min": 14391.3759765625, "max": 43570.23046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989939.0, "min": 29952.0, "max": 989939.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.24299678206443787, "min": -0.09934418648481369, "max": 0.3080359399318695, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 61.96417999267578, "min": -24.032115936279297, "max": 78.54916381835938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007820827886462212, "min": -0.00410684198141098, "max": 0.20898030698299408, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9943110942840576, "min": -1.051351547241211, "max": 50.1552734375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06905471314271752, "min": 0.06528054073051483, "max": 0.07262935256239003, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9667659839980453, "min": 0.5008246017798604, "max": 1.0801594685569094, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011544173797621462, "min": 0.00010201292682153461, "max": 0.013641410959410549, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16161843316670046, "min": 0.0014281809755014845, "max": 0.1909797534317477, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.687383151857143e-06, "min": 7.687383151857143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010762336412599999, "min": 0.00010762336412599999, "max": 0.0033753202748933, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256242857142858, "min": 0.10256242857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435874, "min": 1.3886848, "max": 2.4425744000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002659866142857143, "min": 0.0002659866142857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037238126000000006, "min": 0.0037238126000000006, "max": 0.11252815932999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008609932847321033, "min": 0.008609932847321033, "max": 0.3263355791568756, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12053905427455902, "min": 0.12053905427455902, "max": 2.284348964691162, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 583.0, "min": 540.719298245614, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30316.0, "min": 15984.0, "max": 32603.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9937768981147271, "min": -1.0000000521540642, "max": 1.1748959665000438, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 51.67639870196581, "min": -30.635001718997955, "max": 61.171598352491856, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9937768981147271, "min": -1.0000000521540642, "max": 1.1748959665000438, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 51.67639870196581, "min": -30.635001718997955, "max": 61.171598352491856, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.052078196124057285, "min": 0.052042280712875685, "max": 6.628888854756951, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.708066198450979, "min": 2.708066198450979, "max": 106.06222167611122, "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": "1674160133", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674162039" }, "total": 1906.2638490359998, "count": 1, "self": 0.6242174169999544, "children": { "run_training.setup": { "total": 0.09604703900004097, "count": 1, "self": 0.09604703900004097 }, "TrainerController.start_learning": { "total": 1905.5435845799998, "count": 1, "self": 1.1950246140336276, "children": { "TrainerController._reset_env": { "total": 5.905733139999938, "count": 1, "self": 5.905733139999938 }, "TrainerController.advance": { "total": 1898.3590262799662, "count": 63345, "self": 1.1708549860579751, "children": { "env_step": { "total": 1264.4600614099556, "count": 63345, "self": 1163.199334360852, "children": { "SubprocessEnvManager._take_step": { "total": 100.53560645300149, "count": 63345, "self": 4.147929355039878, "children": { "TorchPolicy.evaluate": { "total": 96.38767709796161, "count": 62554, "self": 32.37688353798944, "children": { "TorchPolicy.sample_actions": { "total": 64.01079355997217, "count": 62554, "self": 64.01079355997217 } } } } }, "workers": { "total": 0.7251205961022151, "count": 63345, "self": 0.0, "children": { "worker_root": { "total": 1901.455764558077, "count": 63345, "is_parallel": true, "self": 834.2207703610534, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017490309999175224, "count": 1, "is_parallel": true, "self": 0.0006678050001482916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010812259997692308, "count": 8, "is_parallel": true, "self": 0.0010812259997692308 } } }, "UnityEnvironment.step": { "total": 0.04376458100000491, "count": 1, "is_parallel": true, "self": 0.0005386910002016521, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000451483000006192, "count": 1, "is_parallel": true, "self": 0.000451483000006192 }, "communicator.exchange": { "total": 0.041083735999791315, "count": 1, "is_parallel": true, "self": 0.041083735999791315 }, "steps_from_proto": { "total": 0.00169067100000575, "count": 1, "is_parallel": true, "self": 0.00042641300001378113, "children": { "_process_rank_one_or_two_observation": { "total": 0.001264257999991969, "count": 8, "is_parallel": true, "self": 0.001264257999991969 } } } } } } }, "UnityEnvironment.step": { "total": 1067.2349941970235, "count": 63344, "is_parallel": true, "self": 26.625452497904007, "children": { "UnityEnvironment._generate_step_input": { "total": 21.860347360077185, "count": 63344, "is_parallel": true, "self": 21.860347360077185 }, "communicator.exchange": { "total": 920.9446860680598, "count": 63344, "is_parallel": true, "self": 920.9446860680598 }, "steps_from_proto": { "total": 97.80450827098252, "count": 63344, "is_parallel": true, "self": 21.388917756962428, "children": { "_process_rank_one_or_two_observation": { "total": 76.4155905140201, "count": 506752, "is_parallel": true, "self": 76.4155905140201 } } } } } } } } } } }, "trainer_advance": { "total": 632.7281098839526, "count": 63345, "self": 2.1098146210488267, "children": { "process_trajectory": { "total": 140.74401549890626, "count": 63345, "self": 140.54485575490617, "children": { "RLTrainer._checkpoint": { "total": 0.19915974400009873, "count": 2, "self": 0.19915974400009873 } } }, "_update_policy": { "total": 489.8742797639975, "count": 447, "self": 183.25977094100972, "children": { "TorchPPOOptimizer.update": { "total": 306.6145088229878, "count": 22827, "self": 306.6145088229878 } } } } } } }, "trainer_threads": { "total": 9.810000847210176e-07, "count": 1, "self": 9.810000847210176e-07 }, "TrainerController._save_models": { "total": 0.08379956499993568, "count": 1, "self": 0.0013273110002955946, "children": { "RLTrainer._checkpoint": { "total": 0.08247225399964009, "count": 1, "self": 0.08247225399964009 } } } } } } }