{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35594111680984497, "min": 0.3461613953113556, "max": 1.4570527076721191, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10638.3681640625, "min": 10384.841796875, "max": 44201.15234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3650670647621155, "min": -0.11311739683151245, "max": 0.4035182297229767, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 96.01264190673828, "min": -26.808822631835938, "max": 107.33584594726562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018011484295129776, "min": 0.0029153083451092243, "max": 0.3900042772293091, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.737020492553711, "min": 0.7608954906463623, "max": 92.43101501464844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06970075355535041, "min": 0.0633668324061691, "max": 0.07355648497069327, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9758105497749058, "min": 0.50149182003057, "max": 1.0884587479197174, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009763881259069811, "min": 0.00017259593206393626, "max": 0.012486893873998367, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13669433762697736, "min": 0.0024163430488951076, "max": 0.17931955715746378, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.595347468249998e-06, "min": 7.595347468249998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010633486455549997, "min": 0.00010633486455549997, "max": 0.0036352414882529, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253175000000002, "min": 0.10253175000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354445000000002, "min": 1.3886848, "max": 2.6173358, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026292182499999995, "min": 0.00026292182499999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036809055499999995, "min": 0.0036809055499999995, "max": 0.12119353529, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010120609775185585, "min": 0.010120609775185585, "max": 0.41265568137168884, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1416885405778885, "min": 0.1416885405778885, "max": 2.888589859008789, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 506.7704918032787, "min": 450.9076923076923, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30913.0, "min": 15984.0, "max": 33403.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2308360434702186, "min": -1.0000000521540642, "max": 1.3647014658842513, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 75.08099865168333, "min": -31.98920165002346, "max": 91.43499821424484, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2308360434702186, "min": -1.0000000521540642, "max": 1.3647014658842513, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 75.08099865168333, "min": -31.98920165002346, "max": 91.43499821424484, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05296870745187931, "min": 0.05017191919744877, "max": 8.304333683103323, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2310911545646377, "min": 3.07193310925868, "max": 132.86933892965317, "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": "1781739437", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781742516" }, "total": 3078.9617160239995, "count": 1, "self": 0.8006007809981384, "children": { "run_training.setup": { "total": 0.02639121300126135, "count": 1, "self": 0.02639121300126135 }, "TrainerController.start_learning": { "total": 3078.13472403, "count": 1, "self": 2.021102609258378, "children": { "TrainerController._reset_env": { "total": 3.1343409159999283, "count": 1, "self": 3.1343409159999283 }, "TrainerController.advance": { "total": 3072.895861940742, "count": 63681, "self": 2.2610821235630283, "children": { "env_step": { "total": 2119.4864100261366, "count": 63681, "self": 1973.1252936381334, "children": { "SubprocessEnvManager._take_step": { "total": 145.0368187609838, "count": 63681, "self": 6.22597357833547, "children": { "TorchPolicy.evaluate": { "total": 138.81084518264834, "count": 62567, "self": 138.81084518264834 } } }, "workers": { "total": 1.324297627019405, "count": 63681, "self": 0.0, "children": { "worker_root": { "total": 3070.886805566108, "count": 63681, "is_parallel": true, "self": 1266.7450732819343, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005319207999491482, "count": 1, "is_parallel": true, "self": 0.0038990379980532452, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014201700014382368, "count": 8, "is_parallel": true, "self": 0.0014201700014382368 } } }, "UnityEnvironment.step": { "total": 0.0814024569990579, "count": 1, "is_parallel": true, "self": 0.0006746790004399372, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005536459993891185, "count": 1, "is_parallel": true, "self": 0.0005536459993891185 }, "communicator.exchange": { "total": 0.07828938099919469, "count": 1, "is_parallel": true, "self": 0.07828938099919469 }, "steps_from_proto": { "total": 0.0018847510000341572, "count": 1, "is_parallel": true, "self": 0.00039818599907448515, "children": { "_process_rank_one_or_two_observation": { "total": 0.001486565000959672, "count": 8, "is_parallel": true, "self": 0.001486565000959672 } } } } } } }, "UnityEnvironment.step": { "total": 1804.1417322841735, "count": 63680, "is_parallel": true, "self": 46.25935951645624, "children": { "UnityEnvironment._generate_step_input": { "total": 29.797233976740245, "count": 63680, "is_parallel": true, "self": 29.797233976740245 }, "communicator.exchange": { "total": 1590.4287348810776, "count": 63680, "is_parallel": true, "self": 1590.4287348810776 }, "steps_from_proto": { "total": 137.65640390989938, "count": 63680, "is_parallel": true, "self": 27.195411567856354, "children": { "_process_rank_one_or_two_observation": { "total": 110.46099234204303, "count": 509440, "is_parallel": true, "self": 110.46099234204303 } } } } } } } } } } }, "trainer_advance": { "total": 951.1483697910426, "count": 63681, "self": 4.07464904895096, "children": { "process_trajectory": { "total": 136.31217278908298, "count": 63681, "self": 135.87137759108555, "children": { "RLTrainer._checkpoint": { "total": 0.4407951979974314, "count": 2, "self": 0.4407951979974314 } } }, "_update_policy": { "total": 810.7615479530086, "count": 456, "self": 316.63814828598515, "children": { "TorchPPOOptimizer.update": { "total": 494.1233996670235, "count": 22806, "self": 494.1233996670235 } } } } } } }, "trainer_threads": { "total": 1.0370004019932821e-06, "count": 1, "self": 1.0370004019932821e-06 }, "TrainerController._save_models": { "total": 0.08341752699925564, "count": 1, "self": 0.0018388560001767473, "children": { "RLTrainer._checkpoint": { "total": 0.0815786709990789, "count": 1, "self": 0.0815786709990789 } } } } } } }