{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3001975417137146, "min": 0.2905435562133789, "max": 0.40185609459877014, "count": 7 }, "Pyramids.Policy.Entropy.sum": { "value": 9058.7607421875, "min": 8651.224609375, "max": 11241.087890625, "count": 7 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 809960.0, "max": 989926.0, "count": 7 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 809960.0, "max": 989926.0, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4600345492362976, "min": 0.40502262115478516, "max": 0.5170003771781921, "count": 7 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.96953582763672, "min": 108.14103698730469, "max": 143.2091064453125, "count": 7 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030832238495349884, "min": -0.012912614271044731, "max": 0.030832238495349884, "count": 7 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.509697914123535, "min": -3.5122311115264893, "max": 8.509697914123535, "count": 7 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.64285714285717, "min": 351.64285714285717, "max": 415.81944444444446, "count": 7 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29538.0, "min": 23555.0, "max": 30950.0, "count": 7 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.553083317443019, "min": 1.389947343029474, "max": 1.5703325310592042, "count": 7 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.45899866521358, "min": 98.75919900089502, "max": 135.04859767109156, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.553083317443019, "min": 1.389947343029474, "max": 1.5703325310592042, "count": 7 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.45899866521358, "min": 98.75919900089502, "max": 135.04859767109156, "count": 7 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03744134823743176, "min": 0.03744134823743176, "max": 0.04378624255760981, "count": 7 }, "Pyramids.Policy.RndReward.sum": { "value": 3.145073251944268, "min": 2.5631008547206875, "max": 3.302659035194665, "count": 7 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06901744256416957, "min": 0.06521061695982805, "max": 0.06981680575887515, "count": 7 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.966244195898374, "min": 0.8023969015824451, "max": 0.9781592543974207, "count": 7 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018192482356209353, "min": 0.014982802643418029, "max": 0.018192482356209353, "count": 7 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25469475298693095, "min": 0.17979363172101634, "max": 0.25469475298693095, "count": 7 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.51439035237857e-06, "min": 7.51439035237857e-06, "max": 6.065330478225833e-05, "count": 7 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010520146493329997, "min": 0.00010520146493329997, "max": 0.0007334531555159999, "count": 7 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250476428571428, "min": 0.10250476428571428, "max": 0.12021774166666667, "count": 7 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350667, "min": 1.4350667, "max": 1.6444839999999998, "count": 7 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002602259521428571, "min": 0.0002602259521428571, "max": 0.0020297523925, "count": 7 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036431633299999996, "min": 0.0036431633299999996, "max": 0.0245639516, "count": 7 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010069741867482662, "min": 0.009762607514858246, "max": 0.010430343449115753, "count": 7 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14097638428211212, "min": 0.12516412138938904, "max": 0.15222415328025818, "count": 7 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679614963", "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 --resume", "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": "1679615772" }, "total": 809.0315722919995, "count": 1, "self": 0.6313388959993063, "children": { "run_training.setup": { "total": 0.13723234999997658, "count": 1, "self": 0.13723234999997658 }, "TrainerController.start_learning": { "total": 808.2630010460002, "count": 1, "self": 0.5253342729747601, "children": { "TrainerController._reset_env": { "total": 4.500169143000221, "count": 1, "self": 4.500169143000221 }, "TrainerController.advance": { "total": 803.1139770020254, "count": 13998, "self": 0.5389865869374262, "children": { "env_step": { "total": 544.9573525120718, "count": 13998, "self": 514.3701943310189, "children": { "SubprocessEnvManager._take_step": { "total": 30.265318044025207, "count": 13998, "self": 1.5033554050160092, "children": { "TorchPolicy.evaluate": { "total": 28.761962639009198, "count": 13558, "self": 28.761962639009198 } } }, "workers": { "total": 0.32184013702772063, "count": 13998, "self": 0.0, "children": { "worker_root": { "total": 806.4989569350123, "count": 13998, "is_parallel": true, "self": 332.2817186190314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002066731000013533, "count": 1, "is_parallel": true, "self": 0.0006390210000972729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014277099999162601, "count": 8, "is_parallel": true, "self": 0.0014277099999162601 } } }, "UnityEnvironment.step": { "total": 0.06863061900003231, "count": 1, "is_parallel": true, "self": 0.0006398000000444881, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005083780001768901, "count": 1, "is_parallel": true, "self": 0.0005083780001768901 }, "communicator.exchange": { "total": 0.06531844599976466, "count": 1, "is_parallel": true, "self": 0.06531844599976466 }, "steps_from_proto": { "total": 0.0021639950000462704, "count": 1, "is_parallel": true, "self": 0.00044409099928088835, "children": { "_process_rank_one_or_two_observation": { "total": 0.001719904000765382, "count": 8, "is_parallel": true, "self": 0.001719904000765382 } } } } } } }, "UnityEnvironment.step": { "total": 474.2172383159809, "count": 13997, "is_parallel": true, "self": 9.655909960993995, "children": { "UnityEnvironment._generate_step_input": { "total": 5.832029992981006, "count": 13997, "is_parallel": true, "self": 5.832029992981006 }, "communicator.exchange": { "total": 429.54272611801525, "count": 13997, "is_parallel": true, "self": 429.54272611801525 }, "steps_from_proto": { "total": 29.186572243990668, "count": 13997, "is_parallel": true, "self": 6.725139010022303, "children": { "_process_rank_one_or_two_observation": { "total": 22.461433233968364, "count": 111976, "is_parallel": true, "self": 22.461433233968364 } } } } } } } } } } }, "trainer_advance": { "total": 257.6176379030162, "count": 13998, "self": 1.066046331015059, "children": { "process_trajectory": { "total": 35.85074399499808, "count": 13998, "self": 35.72269414799757, "children": { "RLTrainer._checkpoint": { "total": 0.12804984700051136, "count": 1, "self": 0.12804984700051136 } } }, "_update_policy": { "total": 220.70084757700306, "count": 102, "self": 90.52184287402224, "children": { "TorchPPOOptimizer.update": { "total": 130.17900470298082, "count": 4908, "self": 130.17900470298082 } } } } } } }, "trainer_threads": { "total": 1.1889997040270828e-06, "count": 1, "self": 1.1889997040270828e-06 }, "TrainerController._save_models": { "total": 0.12351943900011975, "count": 1, "self": 0.002713141000640462, "children": { "RLTrainer._checkpoint": { "total": 0.12080629799947928, "count": 1, "self": 0.12080629799947928 } } } } } } }