{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27600640058517456, "min": 0.23043261468410492, "max": 1.570688247680664, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 8266.943359375, "min": 6901.91748046875, "max": 47648.3984375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999893.0, "min": 29952.0, "max": 2999893.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999893.0, "min": 29952.0, "max": 2999893.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.019980689510703087, "min": -0.057803209871053696, "max": -0.014841057360172272, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -4.795365333557129, "min": -13.699360847473145, "max": -3.5766947269439697, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 7.533539246651344e-06, "min": -0.0647275522351265, "max": 0.0007755510741844773, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.001808049390092492, "min": -15.340429306030273, "max": 0.1861322522163391, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0483908408002915, "min": 0.048189628742810395, "max": 0.07901927963231918, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3387358856020405, "min": 0.21480267124675403, "max": 0.47385560126098647, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 3.418714377586919e-08, "min": 2.8188636585762337e-09, "max": 0.0003997508923809453, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 2.3931000643108435e-07, "min": 1.4094318292881169e-08, "max": 0.0017187783542883307, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 6.615638447380938e-07, "min": 6.615638447380938e-07, "max": 0.0001492416005056, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.6309469131666565e-06, "min": 4.6309469131666565e-06, "max": 0.000835048293301233, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10044097619047619, "min": 0.10044097619047619, "max": 0.19949440000000002, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7030868333333333, "min": 0.7030868333333333, "max": 1.2566987666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.405352142857135e-05, "min": 5.405352142857135e-05, "max": 0.00994949056, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0003783746499999994, "min": 0.0003783746499999994, "max": 0.05568420678999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 7.367919170064852e-05, "min": 5.425821291282773e-05, "max": 0.004382303915917873, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.000515754334628582, "min": 0.00037797712138853967, "max": 0.017529215663671494, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 970.7878787878788, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30969.0, "min": 15984.0, "max": 32594.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9997548900784985, "min": -1.0000000521540642, "max": -0.9111212613907728, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.992401592433453, "min": -32.000001668930054, "max": -16.000000834465027, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9997548900784985, "min": -1.0000000521540642, "max": -0.9111212613907728, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.992401592433453, "min": -32.000001668930054, "max": -16.000000834465027, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0010478565558085598, "min": 0.0008430693783765264, "max": 0.304208040535741, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 0.032483553230065354, "min": 0.01814586204375246, "max": 4.867328648571856, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679690059", "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": "1679707004" }, "total": 16944.532676712, "count": 1, "self": 0.7858074219948321, "children": { "run_training.setup": { "total": 0.18980847199986783, "count": 1, "self": 0.18980847199986783 }, "TrainerController.start_learning": { "total": 16943.557060818002, "count": 1, "self": 3.5689233100347337, "children": { "TrainerController._reset_env": { "total": 6.361216042000024, "count": 1, "self": 6.361216042000024 }, "TrainerController.advance": { "total": 16933.422529141968, "count": 187967, "self": 3.982266632741812, "children": { "env_step": { "total": 3705.8492807940347, "count": 187967, "self": 3378.3614219812516, "children": { "SubprocessEnvManager._take_step": { "total": 325.231521321434, "count": 187967, "self": 13.395671606009728, "children": { "TorchPolicy.evaluate": { "total": 311.8358497154243, "count": 187548, "self": 311.8358497154243 } } }, "workers": { "total": 2.256337491349086, "count": 187967, "self": 0.0, "children": { "worker_root": { "total": 16932.58346035615, "count": 187967, "is_parallel": true, "self": 13870.42099397961, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026546139999936713, "count": 1, "is_parallel": true, "self": 0.000747874999888154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019067390001055173, "count": 8, "is_parallel": true, "self": 0.0019067390001055173 } } }, "UnityEnvironment.step": { "total": 0.04982278200009205, "count": 1, "is_parallel": true, "self": 0.0005469820002872439, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004606749998856685, "count": 1, "is_parallel": true, "self": 0.0004606749998856685 }, "communicator.exchange": { "total": 0.047169891999828906, "count": 1, "is_parallel": true, "self": 0.047169891999828906 }, "steps_from_proto": { "total": 0.0016452330000902293, "count": 1, "is_parallel": true, "self": 0.0003681439998217684, "children": { "_process_rank_one_or_two_observation": { "total": 0.001277089000268461, "count": 8, "is_parallel": true, "self": 0.001277089000268461 } } } } } } }, "UnityEnvironment.step": { "total": 3062.16246637654, "count": 187966, "is_parallel": true, "self": 89.97520318337274, "children": { "UnityEnvironment._generate_step_input": { "total": 65.70185844935554, "count": 187966, "is_parallel": true, "self": 65.70185844935554 }, "communicator.exchange": { "total": 2640.6902524187153, "count": 187966, "is_parallel": true, "self": 2640.6902524187153 }, "steps_from_proto": { "total": 265.79515232509675, "count": 187966, "is_parallel": true, "self": 55.09131508822338, "children": { "_process_rank_one_or_two_observation": { "total": 210.70383723687337, "count": 1503728, "is_parallel": true, "self": 210.70383723687337 } } } } } } } } } } }, "trainer_advance": { "total": 13223.59098171519, "count": 187967, "self": 5.133535870569176, "children": { "process_trajectory": { "total": 348.66421977062487, "count": 187967, "self": 347.73183052962645, "children": { "RLTrainer._checkpoint": { "total": 0.9323892409984182, "count": 6, "self": 0.9323892409984182 } } }, "_update_policy": { "total": 12869.793226073996, "count": 641, "self": 9379.447818775483, "children": { "TorchPPOOptimizer.update": { "total": 3490.345407298514, "count": 367200, "self": 3490.345407298514 } } } } } } }, "trainer_threads": { "total": 1.4359975466504693e-06, "count": 1, "self": 1.4359975466504693e-06 }, "TrainerController._save_models": { "total": 0.2043908880004892, "count": 1, "self": 0.002809901001455728, "children": { "RLTrainer._checkpoint": { "total": 0.20158098699903348, "count": 1, "self": 0.20158098699903348 } } } } } } }