{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3795848786830902, "min": 0.3795848786830902, "max": 1.418249487876892, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11569.7470703125, "min": 11569.7470703125, "max": 43024.015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5120000839233398, "min": -0.09799809008836746, "max": 0.5546813011169434, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.8480224609375, "min": -23.61754035949707, "max": 150.87332153320312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011662984266877174, "min": -0.007957198657095432, "max": 0.36671602725982666, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2539725303649902, "min": -2.116614818572998, "max": 86.91169738769531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07002136019097333, "min": 0.06452416703736434, "max": 0.07306342068269649, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9802990426736266, "min": 0.48882051769292106, "max": 1.0600432780572424, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017041868073907347, "min": 0.0012173934410264452, "max": 0.017041868073907347, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23858615303470285, "min": 0.012001559961934347, "max": 0.23858615303470285, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.348083264957143e-06, "min": 7.348083264957143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010287316570940001, "min": 0.00010287316570940001, "max": 0.0035051693316103, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244932857142856, "min": 0.10244932857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342906, "min": 1.3886848, "max": 2.5683897000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002546879242857143, "min": 0.0002546879242857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035656309400000003, "min": 0.0035656309400000003, "max": 0.11686213103000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013455605134367943, "min": 0.013455605134367943, "max": 0.48834070563316345, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1883784681558609, "min": 0.1883784681558609, "max": 3.4183850288391113, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 359.0722891566265, "min": 347.61176470588236, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29803.0, "min": 15984.0, "max": 33778.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5445132339934269, "min": -1.0000000521540642, "max": 1.6288470362039174, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.19459842145443, "min": -30.556001722812653, "max": 138.45199807733297, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5445132339934269, "min": -1.0000000521540642, "max": 1.6288470362039174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.19459842145443, "min": -30.556001722812653, "max": 138.45199807733297, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05048634798416071, "min": 0.05017663142117896, "max": 10.142194776795805, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.190366882685339, "min": 4.130043850076618, "max": 162.27511642873287, "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": "1721162778", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/john/miniconda3/envs/unit5/bin/mlagents-learn ../config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721163591" }, "total": 813.7426945690022, "count": 1, "self": 0.2177115429949481, "children": { "run_training.setup": { "total": 0.011144151001644786, "count": 1, "self": 0.011144151001644786 }, "TrainerController.start_learning": { "total": 813.5138388750056, "count": 1, "self": 0.5244471678670379, "children": { "TrainerController._reset_env": { "total": 1.4835279479957535, "count": 1, "self": 1.4835279479957535 }, "TrainerController.advance": { "total": 811.4525509161394, "count": 63732, "self": 0.546846641911543, "children": { "env_step": { "total": 511.0022627788203, "count": 63732, "self": 448.16308805214794, "children": { "SubprocessEnvManager._take_step": { "total": 62.49030939936347, "count": 63732, "self": 1.837520797700563, "children": { "TorchPolicy.evaluate": { "total": 60.652788601662905, "count": 62562, "self": 60.652788601662905 } } }, "workers": { "total": 0.34886532730888575, "count": 63732, "self": 0.0, "children": { "worker_root": { "total": 812.5773908156989, "count": 63732, "is_parallel": true, "self": 405.5699800459188, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009686400007922202, "count": 1, "is_parallel": true, "self": 0.0002797600027406588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006888799980515614, "count": 8, "is_parallel": true, "self": 0.0006888799980515614 } } }, "UnityEnvironment.step": { "total": 0.0197421420016326, "count": 1, "is_parallel": true, "self": 0.00022370000078808516, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019113999587716535, "count": 1, "is_parallel": true, "self": 0.00019113999587716535 }, "communicator.exchange": { "total": 0.01866886200150475, "count": 1, "is_parallel": true, "self": 0.01866886200150475 }, "steps_from_proto": { "total": 0.0006584400034626015, "count": 1, "is_parallel": true, "self": 0.00014629999350290745, "children": { "_process_rank_one_or_two_observation": { "total": 0.000512140009959694, "count": 8, "is_parallel": true, "self": 0.000512140009959694 } } } } } } }, "UnityEnvironment.step": { "total": 407.0074107697801, "count": 63731, "is_parallel": true, "self": 12.125774344560341, "children": { "UnityEnvironment._generate_step_input": { "total": 7.940337077438016, "count": 63731, "is_parallel": true, "self": 7.940337077438016 }, "communicator.exchange": { "total": 352.7902035196821, "count": 63731, "is_parallel": true, "self": 352.7902035196821 }, "steps_from_proto": { "total": 34.15109582809964, "count": 63731, "is_parallel": true, "self": 6.89635781058314, "children": { "_process_rank_one_or_two_observation": { "total": 27.2547380175165, "count": 509848, "is_parallel": true, "self": 27.2547380175165 } } } } } } } } } } }, "trainer_advance": { "total": 299.9034414954076, "count": 63732, "self": 0.9817886155142332, "children": { "process_trajectory": { "total": 54.298212747919024, "count": 63732, "self": 54.18650843392243, "children": { "RLTrainer._checkpoint": { "total": 0.1117043139965972, "count": 2, "self": 0.1117043139965972 } } }, "_update_policy": { "total": 244.62344013197435, "count": 451, "self": 138.0963153844059, "children": { "TorchPPOOptimizer.update": { "total": 106.52712474756845, "count": 22791, "self": 106.52712474756845 } } } } } } }, "trainer_threads": { "total": 4.800021997652948e-07, "count": 1, "self": 4.800021997652948e-07 }, "TrainerController._save_models": { "total": 0.053312363001168706, "count": 1, "self": 0.0012631300050998107, "children": { "RLTrainer._checkpoint": { "total": 0.052049232996068895, "count": 1, "self": 0.052049232996068895 } } } } } } }