{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2917984426021576, "min": 0.2814278304576874, "max": 1.4904624223709106, "count": 47 }, "Pyramids.Policy.Entropy.sum": { "value": 8651.240234375, "min": 8456.34375, "max": 45214.66796875, "count": 47 }, "Pyramids.Step.mean": { "value": 1409922.0, "min": 29952.0, "max": 1409922.0, "count": 47 }, "Pyramids.Step.sum": { "value": 1409922.0, "min": 29952.0, "max": 1409922.0, "count": 47 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6881229281425476, "min": -0.08805058896541595, "max": 0.7786554098129272, "count": 47 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 197.4912872314453, "min": -21.308242797851562, "max": 233.59661865234375, "count": 47 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008429104462265968, "min": -0.028382234275341034, "max": 0.26910167932510376, "count": 47 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4191529750823975, "min": -7.3226165771484375, "max": 63.777095794677734, "count": 47 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07113617941615216, "min": 0.06426539978461474, "max": 0.07533700178776469, "count": 47 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9959065118261303, "min": 0.48072699549636033, "max": 1.1120324870959548, "count": 47 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013881878263505528, "min": 0.000716204728954707, "max": 0.014427053621191243, "count": 47 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1943462956890774, "min": 0.005013433102682949, "max": 0.2019787506966774, "count": 47 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016041322510036902, "min": 0.00016041322510036902, "max": 0.00029838354339596195, "count": 47 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0022457851514051663, "min": 0.0020691136102954665, "max": 0.0039379010873663665, "count": 47 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15347105952380954, "min": 0.15347105952380954, "max": 0.19946118095238097, "count": 47 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1485948333333336, "min": 1.3897045333333333, "max": 2.8126336333333333, "count": 47 }, "Pyramids.Policy.Beta.mean": { "value": 0.005351758846428571, "min": 0.005351758846428571, "max": 0.009946171977142856, "count": 47 }, "Pyramids.Policy.Beta.sum": { "value": 0.07492462385, "min": 0.06897148288, "max": 0.13128209997, "count": 47 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006894633173942566, "min": 0.006199497263878584, "max": 0.3654952347278595, "count": 47 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09652486443519592, "min": 0.0867929607629776, "max": 2.558466672897339, "count": 47 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 289.3557692307692, "min": 275.2803738317757, "max": 999.0, "count": 47 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30093.0, "min": 15984.0, "max": 32392.0, "count": 47 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.672868553797404, "min": -1.0000000521540642, "max": 1.7201181678609414, "count": 47 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.65119814872742, "min": -32.000001668930054, "max": 189.21299846470356, "count": 47 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.672868553797404, "min": -1.0000000521540642, "max": 1.7201181678609414, "count": 47 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.65119814872742, "min": -32.000001668930054, "max": 189.21299846470356, "count": 47 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02009038202550506, "min": 0.01863885583337502, "max": 7.280956168659031, "count": 47 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1094901126780314, "min": 1.8851147969253361, "max": 116.4952986985445, "count": 47 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 47 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 47 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721402641", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721406054" }, "total": 3412.7485500880002, "count": 1, "self": 0.37789232600016476, "children": { "run_training.setup": { "total": 0.06134379700000636, "count": 1, "self": 0.06134379700000636 }, "TrainerController.start_learning": { "total": 3412.309313965, "count": 1, "self": 2.3103014090129363, "children": { "TrainerController._reset_env": { "total": 3.481168920000016, "count": 1, "self": 3.481168920000016 }, "TrainerController.advance": { "total": 3406.364838765987, "count": 92515, "self": 2.4798566969793683, "children": { "env_step": { "total": 2461.428590161083, "count": 92515, "self": 2251.1505750670576, "children": { "SubprocessEnvManager._take_step": { "total": 208.86017580803463, "count": 92515, "self": 7.4542210229672605, "children": { "TorchPolicy.evaluate": { "total": 201.40595478506737, "count": 89937, "self": 201.40595478506737 } } }, "workers": { "total": 1.4178392859903965, "count": 92514, "self": 0.0, "children": { "worker_root": { "total": 3404.2882774059426, "count": 92514, "is_parallel": true, "self": 1348.586886185854, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005288166000013916, "count": 1, "is_parallel": true, "self": 0.003765704000045389, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015224619999685274, "count": 8, "is_parallel": true, "self": 0.0015224619999685274 } } }, "UnityEnvironment.step": { "total": 0.06061509599999226, "count": 1, "is_parallel": true, "self": 0.0006790879999698518, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005351579999910427, "count": 1, "is_parallel": true, "self": 0.0005351579999910427 }, "communicator.exchange": { "total": 0.05742662200003679, "count": 1, "is_parallel": true, "self": 0.05742662200003679 }, "steps_from_proto": { "total": 0.001974227999994582, "count": 1, "is_parallel": true, "self": 0.0004049220000297282, "children": { "_process_rank_one_or_two_observation": { "total": 0.001569305999964854, "count": 8, "is_parallel": true, "self": 0.001569305999964854 } } } } } } }, "UnityEnvironment.step": { "total": 2055.7013912200887, "count": 92513, "is_parallel": true, "self": 51.97368869394495, "children": { "UnityEnvironment._generate_step_input": { "total": 35.67988744404278, "count": 92513, "is_parallel": true, "self": 35.67988744404278 }, "communicator.exchange": { "total": 1817.942946104048, "count": 92513, "is_parallel": true, "self": 1817.942946104048 }, "steps_from_proto": { "total": 150.104868978053, "count": 92513, "is_parallel": true, "self": 31.895608715975754, "children": { "_process_rank_one_or_two_observation": { "total": 118.20926026207724, "count": 740104, "is_parallel": true, "self": 118.20926026207724 } } } } } } } } } } }, "trainer_advance": { "total": 942.4563919079244, "count": 92514, "self": 4.591229794925766, "children": { "process_trajectory": { "total": 197.36415376299925, "count": 92514, "self": 197.08736866499936, "children": { "RLTrainer._checkpoint": { "total": 0.27678509799989115, "count": 2, "self": 0.27678509799989115 } } }, "_update_policy": { "total": 740.5010083499994, "count": 655, "self": 441.8711659939811, "children": { "TorchPPOOptimizer.update": { "total": 298.62984235601834, "count": 32820, "self": 298.62984235601834 } } } } } } }, "trainer_threads": { "total": 1.3610001587949228e-06, "count": 1, "self": 1.3610001587949228e-06 }, "TrainerController._save_models": { "total": 0.15300350899997284, "count": 1, "self": 0.001851845000146568, "children": { "RLTrainer._checkpoint": { "total": 0.15115166399982627, "count": 1, "self": 0.15115166399982627 } } } } } } }