{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4323011040687561, "min": 0.4323011040687561, "max": 1.521894097328186, "count": 46 }, "Pyramids.Policy.Entropy.sum": { "value": 13038.201171875, "min": 13038.201171875, "max": 46168.1796875, "count": 46 }, "Pyramids.Step.mean": { "value": 1379889.0, "min": 29952.0, "max": 1379889.0, "count": 46 }, "Pyramids.Step.sum": { "value": 1379889.0, "min": 29952.0, "max": 1379889.0, "count": 46 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6202417612075806, "min": -0.12486793100833893, "max": 0.6453419923782349, "count": 46 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.90817260742188, "min": -29.593700408935547, "max": 179.4050750732422, "count": 46 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012686235830187798, "min": -0.020177382975816727, "max": 0.10471756756305695, "count": 46 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.5775184631347656, "min": -4.782039642333984, "max": 25.341651916503906, "count": 46 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07091114711191202, "min": 0.06393599365570475, "max": 0.07449721325344096, "count": 46 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9927560595667683, "min": 0.4811091471929103, "max": 1.1174581988016143, "count": 46 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013107569443198255, "min": 0.0003153645406325535, "max": 0.014699944187480213, "count": 46 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18350597220477557, "min": 0.004322338205057764, "max": 0.20579921862472297, "count": 46 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016352934549023333, "min": 0.00016352934549023333, "max": 0.00029838354339596195, "count": 46 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0022894108368632666, "min": 0.0020886848037717336, "max": 0.003969584076805333, "count": 46 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15450976666666666, "min": 0.15450976666666666, "max": 0.19946118095238097, "count": 46 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1631367333333333, "min": 1.3962282666666668, "max": 2.7231946666666667, "count": 46 }, "Pyramids.Policy.Beta.mean": { "value": 0.00545552569, "min": 0.00545552569, "max": 0.009946171977142856, "count": 46 }, "Pyramids.Policy.Beta.sum": { "value": 0.07637735966, "min": 0.06962320384, "max": 0.13232714720000002, "count": 46 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005336236208677292, "min": 0.005336236208677292, "max": 0.26477232575416565, "count": 46 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07470730692148209, "min": 0.07470730692148209, "max": 1.8534061908721924, "count": 46 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 297.9375, "min": 297.1546391752577, "max": 999.0, "count": 46 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28602.0, "min": 15984.0, "max": 33129.0, "count": 46 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6535793652700395, "min": -1.0000000521540642, "max": 1.702845345606509, "count": 46 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 160.39719843119383, "min": -30.9994016289711, "max": 165.17599852383137, "count": 46 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6535793652700395, "min": -1.0000000521540642, "max": 1.702845345606509, "count": 46 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 160.39719843119383, "min": -30.9994016289711, "max": 165.17599852383137, "count": 46 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016989419559921743, "min": 0.016989419559921743, "max": 5.501258888281882, "count": 46 }, "Pyramids.Policy.RndReward.sum": { "value": 1.647973697312409, "min": 1.647973697312409, "max": 88.02014221251011, "count": 46 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698107012", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698110176" }, "total": 3164.609970321, "count": 1, "self": 0.4864675460003127, "children": { "run_training.setup": { "total": 0.042338582999946084, "count": 1, "self": 0.042338582999946084 }, "TrainerController.start_learning": { "total": 3164.081164192, "count": 1, "self": 2.0965730678226464, "children": { "TrainerController._reset_env": { "total": 3.4329820379998637, "count": 1, "self": 3.4329820379998637 }, "TrainerController.advance": { "total": 3158.548553360177, "count": 88580, "self": 2.178246579084771, "children": { "env_step": { "total": 2261.430189991037, "count": 88580, "self": 2063.367065181015, "children": { "SubprocessEnvManager._take_step": { "total": 196.76392753203095, "count": 88580, "self": 6.740243861953559, "children": { "TorchPolicy.evaluate": { "total": 190.0236836700774, "count": 86988, "self": 190.0236836700774 } } }, "workers": { "total": 1.2991972779911976, "count": 88579, "self": 0.0, "children": { "worker_root": { "total": 3157.3664632769987, "count": 88579, "is_parallel": true, "self": 1269.1054589470596, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018875400000979425, "count": 1, "is_parallel": true, "self": 0.0006164230001104443, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012711169999874983, "count": 8, "is_parallel": true, "self": 0.0012711169999874983 } } }, "UnityEnvironment.step": { "total": 0.05493908999983432, "count": 1, "is_parallel": true, "self": 0.0005921249999119027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005522349999864673, "count": 1, "is_parallel": true, "self": 0.0005522349999864673 }, "communicator.exchange": { "total": 0.05209911899987674, "count": 1, "is_parallel": true, "self": 0.05209911899987674 }, "steps_from_proto": { "total": 0.0016956110000592162, "count": 1, "is_parallel": true, "self": 0.00036968400013392966, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013259269999252865, "count": 8, "is_parallel": true, "self": 0.0013259269999252865 } } } } } } }, "UnityEnvironment.step": { "total": 1888.2610043299392, "count": 88578, "is_parallel": true, "self": 49.84024531483192, "children": { "UnityEnvironment._generate_step_input": { "total": 36.26995800008808, "count": 88578, "is_parallel": true, "self": 36.26995800008808 }, "communicator.exchange": { "total": 1655.7077670529593, "count": 88578, "is_parallel": true, "self": 1655.7077670529593 }, "steps_from_proto": { "total": 146.44303396205987, "count": 88578, "is_parallel": true, "self": 30.148753674154705, "children": { "_process_rank_one_or_two_observation": { "total": 116.29428028790517, "count": 708624, "is_parallel": true, "self": 116.29428028790517 } } } } } } } } } } }, "trainer_advance": { "total": 894.9401167900551, "count": 88579, "self": 3.96228238894696, "children": { "process_trajectory": { "total": 179.12121907810092, "count": 88579, "self": 178.95132169610156, "children": { "RLTrainer._checkpoint": { "total": 0.16989738199936255, "count": 2, "self": 0.16989738199936255 } } }, "_update_policy": { "total": 711.8566153230072, "count": 635, "self": 419.2086930179803, "children": { "TorchPPOOptimizer.update": { "total": 292.6479223050269, "count": 31677, "self": 292.6479223050269 } } } } } } }, "trainer_threads": { "total": 1.1800002539530396e-06, "count": 1, "self": 1.1800002539530396e-06 }, "TrainerController._save_models": { "total": 0.0030545460003850167, "count": 1, "self": 2.3812000108591747e-05, "children": { "RLTrainer._checkpoint": { "total": 0.003030734000276425, "count": 1, "self": 0.003030734000276425 } } } } } } }