{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4463076591491699, "min": 0.4463076591491699, "max": 1.451271653175354, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13232.1298828125, "min": 13232.1298828125, "max": 44025.77734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5139243602752686, "min": -0.11815056204795837, "max": 0.6591110229492188, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.27349853515625, "min": -28.474285125732422, "max": 191.8013153076172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017849331721663475, "min": -0.016980228945612907, "max": 0.46798673272132874, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.8371686935424805, "min": -4.822384834289551, "max": 110.91285705566406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06664664105240567, "min": 0.06588569055855958, "max": 0.07622754945364618, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9330529747336793, "min": 0.5056262982868049, "max": 1.0671856923510465, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01708185617116258, "min": 0.00036055978082329804, "max": 0.01883193338359152, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2391459863962761, "min": 0.003966157589056278, "max": 0.26364706737028126, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.584247471950003e-06, "min": 7.584247471950003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010617946460730003, "min": 0.00010617946460730003, "max": 0.0031262136579289002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252805000000001, "min": 0.10252805000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353927000000002, "min": 1.3691136000000002, "max": 2.4420711, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002625521950000001, "min": 0.0002625521950000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003675730730000001, "min": 0.003675730730000001, "max": 0.10424290289, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012062830850481987, "min": 0.012062830850481987, "max": 0.4838341176509857, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16887962818145752, "min": 0.16887962818145752, "max": 3.386838912963867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 339.7375, "min": 286.1354166666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27179.0, "min": 15984.0, "max": 33135.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5134320882735428, "min": -1.0000000521540642, "max": 1.6930291554890573, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.58799915015697, "min": -32.000001668930054, "max": 172.24739744514227, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5134320882735428, "min": -1.0000000521540642, "max": 1.6930291554890573, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.58799915015697, "min": -32.000001668930054, "max": 172.24739744514227, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04253644744878531, "min": 0.036786797112830914, "max": 10.280197015032172, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4454522433516104, "min": 3.4454522433516104, "max": 164.48315224051476, "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": "1684681483", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684683951" }, "total": 2468.1022267670005, "count": 1, "self": 0.428998553000838, "children": { "run_training.setup": { "total": 0.03998083999977098, "count": 1, "self": 0.03998083999977098 }, "TrainerController.start_learning": { "total": 2467.633247374, "count": 1, "self": 1.6768607518465615, "children": { "TrainerController._reset_env": { "total": 4.099774212999819, "count": 1, "self": 4.099774212999819 }, "TrainerController.advance": { "total": 2461.765867945154, "count": 63920, "self": 1.6768208061080259, "children": { "env_step": { "total": 1770.3404399829956, "count": 63920, "self": 1640.8097241179971, "children": { "SubprocessEnvManager._take_step": { "total": 128.5219070018993, "count": 63920, "self": 5.367894645834895, "children": { "TorchPolicy.evaluate": { "total": 123.15401235606441, "count": 62560, "self": 123.15401235606441 } } }, "workers": { "total": 1.0088088630991479, "count": 63920, "self": 0.0, "children": { "worker_root": { "total": 2461.5181477290093, "count": 63920, "is_parallel": true, "self": 950.9895878650168, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017500529997960257, "count": 1, "is_parallel": true, "self": 0.0005895490003240411, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011605039994719846, "count": 8, "is_parallel": true, "self": 0.0011605039994719846 } } }, "UnityEnvironment.step": { "total": 0.055153494000023784, "count": 1, "is_parallel": true, "self": 0.0005510750006578746, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048821099971974036, "count": 1, "is_parallel": true, "self": 0.00048821099971974036 }, "communicator.exchange": { "total": 0.04588854299981904, "count": 1, "is_parallel": true, "self": 0.04588854299981904 }, "steps_from_proto": { "total": 0.008225664999827131, "count": 1, "is_parallel": true, "self": 0.00038531499967575655, "children": { "_process_rank_one_or_two_observation": { "total": 0.007840350000151375, "count": 8, "is_parallel": true, "self": 0.007840350000151375 } } } } } } }, "UnityEnvironment.step": { "total": 1510.5285598639925, "count": 63919, "is_parallel": true, "self": 35.19705339496204, "children": { "UnityEnvironment._generate_step_input": { "total": 25.071184360952884, "count": 63919, "is_parallel": true, "self": 25.071184360952884 }, "communicator.exchange": { "total": 1342.3447762160522, "count": 63919, "is_parallel": true, "self": 1342.3447762160522 }, "steps_from_proto": { "total": 107.91554589202542, "count": 63919, "is_parallel": true, "self": 22.716160704972935, "children": { "_process_rank_one_or_two_observation": { "total": 85.19938518705248, "count": 511352, "is_parallel": true, "self": 85.19938518705248 } } } } } } } } } } }, "trainer_advance": { "total": 689.7486071560502, "count": 63920, "self": 3.063617243110457, "children": { "process_trajectory": { "total": 115.46756364894281, "count": 63920, "self": 115.25368856794239, "children": { "RLTrainer._checkpoint": { "total": 0.21387508100042396, "count": 2, "self": 0.21387508100042396 } } }, "_update_policy": { "total": 571.2174262639969, "count": 443, "self": 368.5591770290098, "children": { "TorchPPOOptimizer.update": { "total": 202.65824923498712, "count": 22842, "self": 202.65824923498712 } } } } } } }, "trainer_threads": { "total": 1.1860001905006357e-06, "count": 1, "self": 1.1860001905006357e-06 }, "TrainerController._save_models": { "total": 0.09074327799953608, "count": 1, "self": 0.0013477629991029971, "children": { "RLTrainer._checkpoint": { "total": 0.08939551500043308, "count": 1, "self": 0.08939551500043308 } } } } } } }