{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5382044911384583, "min": 0.5382044911384583, "max": 1.4149174690246582, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16240.859375, "min": 16240.859375, "max": 42922.9375, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3269990086555481, "min": -0.12439348548650742, "max": 0.444025456905365, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 85.67373657226562, "min": -29.978830337524414, "max": 116.33467102050781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0768527090549469, "min": -0.0768527090549469, "max": 0.436563104391098, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -20.13541030883789, "min": -20.13541030883789, "max": 103.4654541015625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06700068741827467, "min": 0.06495718547805682, "max": 0.0724338465483977, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9380096238558454, "min": 0.5070369258387839, "max": 1.0688443103281315, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016087938324482354, "min": 0.00033989349804842576, "max": 0.016087938324482354, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22523113654275295, "min": 0.004418615474629535, "max": 0.22523113654275295, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.720918854964281e-06, "min": 7.720918854964281e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010809286396949993, "min": 0.00010809286396949993, "max": 0.0034878724373759, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257360714285715, "min": 0.10257360714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360305000000002, "min": 1.3886848, "max": 2.5264778999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002671033535714284, "min": 0.0002671033535714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003739446949999998, "min": 0.003739446949999998, "max": 0.11627614759, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009574966505169868, "min": 0.009574966505169868, "max": 0.5374106168746948, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13404953479766846, "min": 0.13404953479766846, "max": 3.7618744373321533, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 481.6666666666667, "min": 442.77272727272725, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30345.0, "min": 15984.0, "max": 32758.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3595587083744625, "min": -1.0000000521540642, "max": 1.4142301099961752, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 85.65219862759113, "min": -31.994401678442955, "max": 103.23879802972078, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3595587083744625, "min": -1.0000000521540642, "max": 1.4142301099961752, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 85.65219862759113, "min": -31.994401678442955, "max": 103.23879802972078, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04782726125521881, "min": 0.04628086857443962, "max": 10.419472372159362, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.013117459078785, "min": 3.0082564573385753, "max": 166.7115579545498, "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": "1715297344", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715299686" }, "total": 2342.044186017, "count": 1, "self": 0.4773700790001385, "children": { "run_training.setup": { "total": 0.05417509999995218, "count": 1, "self": 0.05417509999995218 }, "TrainerController.start_learning": { "total": 2341.5126408379997, "count": 1, "self": 1.7366608020047352, "children": { "TrainerController._reset_env": { "total": 2.1229352090000475, "count": 1, "self": 2.1229352090000475 }, "TrainerController.advance": { "total": 2337.568488297995, "count": 63559, "self": 1.7293274900157485, "children": { "env_step": { "total": 1675.4447242679996, "count": 63559, "self": 1523.4197184790369, "children": { "SubprocessEnvManager._take_step": { "total": 150.98284357397233, "count": 63559, "self": 5.389817843975834, "children": { "TorchPolicy.evaluate": { "total": 145.5930257299965, "count": 62559, "self": 145.5930257299965 } } }, "workers": { "total": 1.0421622149904124, "count": 63559, "self": 0.0, "children": { "worker_root": { "total": 2335.7624783960305, "count": 63559, "is_parallel": true, "self": 953.6687857870643, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002286460999926021, "count": 1, "is_parallel": true, "self": 0.0007588289998921027, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015276320000339183, "count": 8, "is_parallel": true, "self": 0.0015276320000339183 } } }, "UnityEnvironment.step": { "total": 0.05012227600002461, "count": 1, "is_parallel": true, "self": 0.0006560690000014802, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004883560000052967, "count": 1, "is_parallel": true, "self": 0.0004883560000052967 }, "communicator.exchange": { "total": 0.04718212399995991, "count": 1, "is_parallel": true, "self": 0.04718212399995991 }, "steps_from_proto": { "total": 0.0017957270000579229, "count": 1, "is_parallel": true, "self": 0.0003937730000416195, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014019540000163033, "count": 8, "is_parallel": true, "self": 0.0014019540000163033 } } } } } } }, "UnityEnvironment.step": { "total": 1382.0936926089662, "count": 63558, "is_parallel": true, "self": 37.21569593396907, "children": { "UnityEnvironment._generate_step_input": { "total": 25.458306299022638, "count": 63558, "is_parallel": true, "self": 25.458306299022638 }, "communicator.exchange": { "total": 1208.6264515279938, "count": 63558, "is_parallel": true, "self": 1208.6264515279938 }, "steps_from_proto": { "total": 110.79323884798089, "count": 63558, "is_parallel": true, "self": 23.654641804951893, "children": { "_process_rank_one_or_two_observation": { "total": 87.138597043029, "count": 508464, "is_parallel": true, "self": 87.138597043029 } } } } } } } } } } }, "trainer_advance": { "total": 660.3944365399794, "count": 63559, "self": 3.145080124931269, "children": { "process_trajectory": { "total": 137.84306093105351, "count": 63559, "self": 137.63400724805342, "children": { "RLTrainer._checkpoint": { "total": 0.20905368300009286, "count": 2, "self": 0.20905368300009286 } } }, "_update_policy": { "total": 519.4062954839947, "count": 451, "self": 309.44675790802694, "children": { "TorchPPOOptimizer.update": { "total": 209.95953757596772, "count": 22788, "self": 209.95953757596772 } } } } } } }, "trainer_threads": { "total": 1.1400002222217154e-06, "count": 1, "self": 1.1400002222217154e-06 }, "TrainerController._save_models": { "total": 0.08455538899988824, "count": 1, "self": 0.0013446749999275198, "children": { "RLTrainer._checkpoint": { "total": 0.08321071399996072, "count": 1, "self": 0.08321071399996072 } } } } } } }