{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2540161907672882, "min": 0.24502567946910858, "max": 1.5282164812088013, "count": 43 }, "Pyramids.Policy.Entropy.sum": { "value": 7543.2646484375, "min": 7374.29296875, "max": 46359.9765625, "count": 43 }, "Pyramids.Step.mean": { "value": 1289955.0, "min": 29952.0, "max": 1289955.0, "count": 43 }, "Pyramids.Step.sum": { "value": 1289955.0, "min": 29952.0, "max": 1289955.0, "count": 43 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.722827672958374, "min": -0.11745752394199371, "max": 0.7676102519035339, "count": 43 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 211.065673828125, "min": -27.837432861328125, "max": 227.98023986816406, "count": 43 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013024535030126572, "min": -0.022872503846883774, "max": 0.2180640995502472, "count": 43 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.80316424369812, "min": -6.175576210021973, "max": 51.681190490722656, "count": 43 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07214627591227847, "min": 0.06464061130550579, "max": 0.07352088584170606, "count": 43 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0100478627718985, "min": 0.4989326294881543, "max": 1.0771654536365531, "count": 43 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015483656162922712, "min": 0.00041915573043584543, "max": 0.01707032203953289, "count": 43 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21677118628091796, "min": 0.0041915573043584545, "max": 0.24851815752723874, "count": 43 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.728779409120883e-06, "min": 5.728779409120883e-06, "max": 0.00029626971552914287, "count": 43 }, "Pyramids.Policy.LearningRate.sum": { "value": 8.020291172769236e-05, "min": 8.020291172769236e-05, "max": 0.0036688612539693844, "count": 43 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10190956043956045, "min": 0.10190956043956045, "max": 0.19875657142857145, "count": 43 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4267338461538464, "min": 1.391296, "max": 2.6711099230769233, "count": 43 }, "Pyramids.Policy.Beta.mean": { "value": 0.00020076508791208803, "min": 0.00020076508791208803, "max": 0.009875781485714285, "count": 43 }, "Pyramids.Policy.Beta.sum": { "value": 0.0028107112307692323, "min": 0.0028107112307692323, "max": 0.12231307386153846, "count": 43 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009098507463932037, "min": 0.009098507463932037, "max": 0.2769124507904053, "count": 43 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12737910449504852, "min": 0.12737910449504852, "max": 1.938387155532837, "count": 43 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 246.50819672131146, "min": 237.95934959349594, "max": 999.0, "count": 43 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30074.0, "min": 15984.0, "max": 32746.0, "count": 43 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7036479138884664, "min": -1.0000000521540642, "max": 1.745848370776061, "count": 43 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 206.14139758050442, "min": -31.999601677060127, "max": 216.48519797623158, "count": 43 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7036479138884664, "min": -1.0000000521540642, "max": 1.745848370776061, "count": 43 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 206.14139758050442, "min": -31.999601677060127, "max": 216.48519797623158, "count": 43 }, "Pyramids.Policy.RndReward.mean": { "value": 0.023374768659281966, "min": 0.022611881256917484, "max": 5.504442959092557, "count": 43 }, "Pyramids.Policy.RndReward.sum": { "value": 2.828347007773118, "min": 2.7967456683545606, "max": 88.07108734548092, "count": 43 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 43 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 43 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691494627", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691497783" }, "total": 3156.2783641739998, "count": 1, "self": 0.48922240199954103, "children": { "run_training.setup": { "total": 0.07127120199993442, "count": 1, "self": 0.07127120199993442 }, "TrainerController.start_learning": { "total": 3155.7178705700003, "count": 1, "self": 2.0972990098807713, "children": { "TrainerController._reset_env": { "total": 4.518846133999887, "count": 1, "self": 4.518846133999887 }, "TrainerController.advance": { "total": 3149.00527984612, "count": 83733, "self": 2.017264757092562, "children": { "env_step": { "total": 2285.4107278749498, "count": 83733, "self": 2131.4143855990724, "children": { "SubprocessEnvManager._take_step": { "total": 152.75520402384564, "count": 83733, "self": 6.5277860818252975, "children": { "TorchPolicy.evaluate": { "total": 146.22741794202034, "count": 81324, "self": 146.22741794202034 } } }, "workers": { "total": 1.2411382520315328, "count": 83733, "self": 0.0, "children": { "worker_root": { "total": 3148.288533595948, "count": 83733, "is_parallel": true, "self": 1177.1355219179757, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017950189999282884, "count": 1, "is_parallel": true, "self": 0.0005277429997931904, "children": { "_process_rank_one_or_two_observation": { "total": 0.001267276000135098, "count": 8, "is_parallel": true, "self": 0.001267276000135098 } } }, "UnityEnvironment.step": { "total": 0.04874380299997938, "count": 1, "is_parallel": true, "self": 0.0006185550000736839, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005210699998769996, "count": 1, "is_parallel": true, "self": 0.0005210699998769996 }, "communicator.exchange": { "total": 0.04554997800005367, "count": 1, "is_parallel": true, "self": 0.04554997800005367 }, "steps_from_proto": { "total": 0.002054199999975026, "count": 1, "is_parallel": true, "self": 0.000402667000571455, "children": { "_process_rank_one_or_two_observation": { "total": 0.001651532999403571, "count": 8, "is_parallel": true, "self": 0.001651532999403571 } } } } } } }, "UnityEnvironment.step": { "total": 1971.1530116779725, "count": 83732, "is_parallel": true, "self": 45.47871829991868, "children": { "UnityEnvironment._generate_step_input": { "total": 30.47792158603329, "count": 83732, "is_parallel": true, "self": 30.47792158603329 }, "communicator.exchange": { "total": 1754.167368236101, "count": 83732, "is_parallel": true, "self": 1754.167368236101 }, "steps_from_proto": { "total": 141.02900355591942, "count": 83732, "is_parallel": true, "self": 27.91556181944111, "children": { "_process_rank_one_or_two_observation": { "total": 113.11344173647831, "count": 669856, "is_parallel": true, "self": 113.11344173647831 } } } } } } } } } } }, "trainer_advance": { "total": 861.5772872140781, "count": 83733, "self": 3.8900196061267707, "children": { "process_trajectory": { "total": 148.9169876569547, "count": 83733, "self": 148.68239522495446, "children": { "RLTrainer._checkpoint": { "total": 0.23459243200022684, "count": 2, "self": 0.23459243200022684 } } }, "_update_policy": { "total": 708.7702799509966, "count": 594, "self": 461.2947369929907, "children": { "TorchPPOOptimizer.update": { "total": 247.47554295800592, "count": 29643, "self": 247.47554295800592 } } } } } } }, "trainer_threads": { "total": 9.169998520519584e-07, "count": 1, "self": 9.169998520519584e-07 }, "TrainerController._save_models": { "total": 0.09644466299960186, "count": 1, "self": 0.0013628069991682423, "children": { "RLTrainer._checkpoint": { "total": 0.09508185600043362, "count": 1, "self": 0.09508185600043362 } } } } } } }