{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7622014880180359, "min": 0.7622014880180359, "max": 1.4947810173034668, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 22866.044921875, "min": 22866.044921875, "max": 45345.67578125, "count": 16 }, "Pyramids.Step.mean": { "value": 479958.0, "min": 29952.0, "max": 479958.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479958.0, "min": 29952.0, "max": 479958.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.11931455135345459, "min": -0.10810833424329758, "max": 0.11931455135345459, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 29.470693588256836, "min": -26.054107666015625, "max": 29.470693588256836, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02010197564959526, "min": 0.016924135386943817, "max": 0.33674222230911255, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.965188026428223, "min": 4.163337230682373, "max": 79.80790710449219, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06957831286629475, "min": 0.06743640038898559, "max": 0.07298853299369869, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9740963801281265, "min": 0.49715757342028677, "max": 1.0224803745091493, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00888321748767201, "min": 0.00041434131570072444, "max": 0.00888321748767201, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12436504482740814, "min": 0.004143413157007244, "max": 0.12436504482740814, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.1146407236942858e-05, "min": 2.1146407236942858e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002960497013172, "min": 0.0002960497013172, "max": 0.0028181530606158005, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10704877142857143, "min": 0.10704877142857143, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4986828, "min": 1.3773696000000002, "max": 2.3393842, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007141722657142861, "min": 0.0007141722657142861, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.009998411720000005, "min": 0.009998411720000005, "max": 0.09398448157999999, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01726623997092247, "min": 0.01726623997092247, "max": 0.4138633608818054, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24172736704349518, "min": 0.24172736704349518, "max": 2.897043466567993, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 684.95, "min": 684.95, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27398.0, "min": 15984.0, "max": 32856.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5148349590599537, "min": -1.0000000521540642, "max": 0.5148349590599537, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 20.593398362398148, "min": -31.998801663517952, "max": 20.593398362398148, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5148349590599537, "min": -1.0000000521540642, "max": 0.5148349590599537, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 20.593398362398148, "min": -31.998801663517952, "max": 20.593398362398148, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12102305980224629, "min": 0.12102305980224629, "max": 8.450660973787308, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 4.840922392089851, "min": 4.840922392089851, "max": 135.21057558059692, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679810446", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679811465" }, "total": 1019.049810386, "count": 1, "self": 0.4790944699998363, "children": { "run_training.setup": { "total": 0.11295210300022518, "count": 1, "self": 0.11295210300022518 }, "TrainerController.start_learning": { "total": 1018.4577638129999, "count": 1, "self": 0.6879317299494687, "children": { "TrainerController._reset_env": { "total": 6.233225589000085, "count": 1, "self": 6.233225589000085 }, "TrainerController.advance": { "total": 1011.4427589380507, "count": 31617, "self": 0.7098029719404622, "children": { "env_step": { "total": 692.4130513320588, "count": 31617, "self": 638.2096046250845, "children": { "SubprocessEnvManager._take_step": { "total": 53.80304936900984, "count": 31617, "self": 2.3255115189690514, "children": { "TorchPolicy.evaluate": { "total": 51.47753785004079, "count": 31301, "self": 51.47753785004079 } } }, "workers": { "total": 0.40039733796447763, "count": 31617, "self": 0.0, "children": { "worker_root": { "total": 1016.3022656439971, "count": 31617, "is_parallel": true, "self": 433.40431974001876, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020456089996514493, "count": 1, "is_parallel": true, "self": 0.0006285420008680376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014170669987834117, "count": 8, "is_parallel": true, "self": 0.0014170669987834117 } } }, "UnityEnvironment.step": { "total": 0.05060372600019036, "count": 1, "is_parallel": true, "self": 0.000529204000486061, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005144489996382617, "count": 1, "is_parallel": true, "self": 0.0005144489996382617 }, "communicator.exchange": { "total": 0.048002083000028506, "count": 1, "is_parallel": true, "self": 0.048002083000028506 }, "steps_from_proto": { "total": 0.0015579900000375346, "count": 1, "is_parallel": true, "self": 0.00035045100003117113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012075390000063635, "count": 8, "is_parallel": true, "self": 0.0012075390000063635 } } } } } } }, "UnityEnvironment.step": { "total": 582.8979459039783, "count": 31616, "is_parallel": true, "self": 15.498552362925693, "children": { "UnityEnvironment._generate_step_input": { "total": 11.705513485012489, "count": 31616, "is_parallel": true, "self": 11.705513485012489 }, "communicator.exchange": { "total": 510.2215349060202, "count": 31616, "is_parallel": true, "self": 510.2215349060202 }, "steps_from_proto": { "total": 45.47234515001992, "count": 31616, "is_parallel": true, "self": 9.530273194005531, "children": { "_process_rank_one_or_two_observation": { "total": 35.94207195601439, "count": 252928, "is_parallel": true, "self": 35.94207195601439 } } } } } } } } } } }, "trainer_advance": { "total": 318.31990463405145, "count": 31617, "self": 1.1105961770404065, "children": { "process_trajectory": { "total": 58.72250292601257, "count": 31617, "self": 58.61604151901247, "children": { "RLTrainer._checkpoint": { "total": 0.1064614070000971, "count": 1, "self": 0.1064614070000971 } } }, "_update_policy": { "total": 258.4868055309985, "count": 209, "self": 163.51999171598482, "children": { "TorchPPOOptimizer.update": { "total": 94.96681381501367, "count": 11403, "self": 94.96681381501367 } } } } } } }, "trainer_threads": { "total": 9.440000212634914e-07, "count": 1, "self": 9.440000212634914e-07 }, "TrainerController._save_models": { "total": 0.09384661199965194, "count": 1, "self": 0.0014019869995536283, "children": { "RLTrainer._checkpoint": { "total": 0.09244462500009831, "count": 1, "self": 0.09244462500009831 } } } } } } }