{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34012624621391296, "min": 0.34012624621391296, "max": 1.4472651481628418, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10247.3232421875, "min": 10198.7109375, "max": 43904.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989877.0, "min": 29952.0, "max": 989877.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.661891758441925, "min": -0.10298196971416473, "max": 0.6790854930877686, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.32969665527344, "min": -24.715673446655273, "max": 190.14393615722656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025487368926405907, "min": -0.0023457661736756563, "max": 0.23767219483852386, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.136463165283203, "min": -0.6450856924057007, "max": 57.27899932861328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07053033528126859, "min": 0.06458787240026133, "max": 0.07332002862426061, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9874246939377602, "min": 0.5107161783659763, "max": 1.0306079621077513, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015463294134053325, "min": 0.0006464163297826209, "max": 0.01636083257889717, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21648611787674654, "min": 0.007756995957391452, "max": 0.22905165610456038, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.70054029032857e-06, "min": 7.70054029032857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010780756406459998, "min": 0.00010780756406459998, "max": 0.0032557319147560994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025668142857143, "min": 0.1025668142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359354000000002, "min": 1.3886848, "max": 2.4846036000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026642474714285715, "min": 0.00026642474714285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00372994646, "min": 0.00372994646, "max": 0.10854586560999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010391195304691792, "min": 0.010217137634754181, "max": 0.34265372157096863, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14547672867774963, "min": 0.14303992688655853, "max": 2.398576021194458, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 284.68518518518516, "min": 278.97115384615387, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30746.0, "min": 15984.0, "max": 32470.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7153147959874735, "min": -1.0000000521540642, "max": 1.7153147959874735, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.25399796664715, "min": -30.500001713633537, "max": 185.25399796664715, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7153147959874735, "min": -1.0000000521540642, "max": 1.7153147959874735, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.25399796664715, "min": -30.500001713633537, "max": 185.25399796664715, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030758750888506055, "min": 0.029711201017912223, "max": 6.671467285603285, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.321945095958654, "min": 3.089964905862871, "max": 106.74347656965256, "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": "1687731260", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687733449" }, "total": 2189.714267534, "count": 1, "self": 0.8013754310004515, "children": { "run_training.setup": { "total": 0.06417761499983499, "count": 1, "self": 0.06417761499983499 }, "TrainerController.start_learning": { "total": 2188.848714488, "count": 1, "self": 1.289033193965679, "children": { "TrainerController._reset_env": { "total": 4.469420987999911, "count": 1, "self": 4.469420987999911 }, "TrainerController.advance": { "total": 2182.998306460034, "count": 64159, "self": 1.3089949719928882, "children": { "env_step": { "total": 1544.1480910289959, "count": 64159, "self": 1436.4642852819752, "children": { "SubprocessEnvManager._take_step": { "total": 106.9363021280767, "count": 64159, "self": 4.681574268053055, "children": { "TorchPolicy.evaluate": { "total": 102.25472786002365, "count": 62574, "self": 102.25472786002365 } } }, "workers": { "total": 0.7475036189439379, "count": 64159, "self": 0.0, "children": { "worker_root": { "total": 2183.934994684959, "count": 64159, "is_parallel": true, "self": 856.4198722999759, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017832250000537897, "count": 1, "is_parallel": true, "self": 0.0005225599995810626, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012606650004727271, "count": 8, "is_parallel": true, "self": 0.0012606650004727271 } } }, "UnityEnvironment.step": { "total": 0.049105193000059444, "count": 1, "is_parallel": true, "self": 0.0005582420001246646, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005172090000087337, "count": 1, "is_parallel": true, "self": 0.0005172090000087337 }, "communicator.exchange": { "total": 0.0461079219999192, "count": 1, "is_parallel": true, "self": 0.0461079219999192 }, "steps_from_proto": { "total": 0.0019218200000068464, "count": 1, "is_parallel": true, "self": 0.0003678440000385308, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015539759999683156, "count": 8, "is_parallel": true, "self": 0.0015539759999683156 } } } } } } }, "UnityEnvironment.step": { "total": 1327.515122384983, "count": 64158, "is_parallel": true, "self": 32.85334544796797, "children": { "UnityEnvironment._generate_step_input": { "total": 22.752136148011687, "count": 64158, "is_parallel": true, "self": 22.752136148011687 }, "communicator.exchange": { "total": 1172.2354564450086, "count": 64158, "is_parallel": true, "self": 1172.2354564450086 }, "steps_from_proto": { "total": 99.67418434399474, "count": 64158, "is_parallel": true, "self": 19.26990804514662, "children": { "_process_rank_one_or_two_observation": { "total": 80.40427629884812, "count": 513264, "is_parallel": true, "self": 80.40427629884812 } } } } } } } } } } }, "trainer_advance": { "total": 637.5412204590455, "count": 64159, "self": 2.5279131050208434, "children": { "process_trajectory": { "total": 107.49760781902319, "count": 64159, "self": 107.29727166602311, "children": { "RLTrainer._checkpoint": { "total": 0.20033615300008023, "count": 2, "self": 0.20033615300008023 } } }, "_update_policy": { "total": 527.5156995350014, "count": 448, "self": 336.7998587690174, "children": { "TorchPPOOptimizer.update": { "total": 190.715840765984, "count": 22800, "self": 190.715840765984 } } } } } } }, "trainer_threads": { "total": 8.820002221909817e-07, "count": 1, "self": 8.820002221909817e-07 }, "TrainerController._save_models": { "total": 0.09195296400002917, "count": 1, "self": 0.0013966740002615552, "children": { "RLTrainer._checkpoint": { "total": 0.09055628999976761, "count": 1, "self": 0.09055628999976761 } } } } } } }