{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12201789766550064, "min": 0.1162334531545639, "max": 1.4231758117675781, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 3656.63232421875, "min": 3470.265869140625, "max": 43173.4609375, "count": 66 }, "Pyramids.Step.mean": { "value": 1979939.0, "min": 29952.0, "max": 1979939.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979939.0, "min": 29952.0, "max": 1979939.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7163037061691284, "min": -0.1145738810300827, "max": 0.7578694224357605, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 213.45849609375, "min": -27.6123046875, "max": 219.78213500976562, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01568666100502014, "min": -0.04293874278664589, "max": 0.20520459115505219, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.674624919891357, "min": -12.065786361694336, "max": 49.24910354614258, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06586870402956958, "min": 0.06492172572429158, "max": 0.07302671383755902, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9221618564139741, "min": 0.48301114987792054, "max": 1.087491127228086, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017118811689821694, "min": 0.0005588025863896641, "max": 0.017118811689821694, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23966336365750374, "min": 0.0040111684581628565, "max": 0.2462204870452315, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.254083962957143e-06, "min": 5.254083962957143e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.35571754814e-05, "min": 7.35571754814e-05, "max": 0.0036653787282071495, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10175132857142859, "min": 0.10175132857142859, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4245186000000003, "min": 1.3845568000000001, "max": 2.7185962499999996, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018495772428571427, "min": 0.00018495772428571427, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.00258940814, "min": 0.00258940814, "max": 0.122197105715, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005794492084532976, "min": 0.005409873556345701, "max": 0.3504163920879364, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08112289011478424, "min": 0.07573822885751724, "max": 2.4529147148132324, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 253.7741935483871, "min": 242.63636363636363, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31468.0, "min": 15984.0, "max": 33090.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6816999856983461, "min": -1.0000000521540642, "max": 1.7401131017774831, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 208.53079822659492, "min": -32.000001668930054, "max": 212.29379841685295, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6816999856983461, "min": -1.0000000521540642, "max": 1.7401131017774831, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 208.53079822659492, "min": -32.000001668930054, "max": 212.29379841685295, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01551090663281596, "min": 0.01551090663281596, "max": 6.4061873108148575, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9233524224691791, "min": 1.629212902758809, "max": 102.49899697303772, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691852573", "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": "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": "1691857564" }, "total": 4990.637692262, "count": 1, "self": 0.47578952699950605, "children": { "run_training.setup": { "total": 0.039583553000284155, "count": 1, "self": 0.039583553000284155 }, "TrainerController.start_learning": { "total": 4990.122319182001, "count": 1, "self": 3.1903466649564507, "children": { "TrainerController._reset_env": { "total": 4.056172492999849, "count": 1, "self": 4.056172492999849 }, "TrainerController.advance": { "total": 4982.7631972880445, "count": 129393, "self": 3.060031553131921, "children": { "env_step": { "total": 3640.204548487884, "count": 129393, "self": 3399.127559221717, "children": { "SubprocessEnvManager._take_step": { "total": 239.20742002299676, "count": 129393, "self": 10.167258451162525, "children": { "TorchPolicy.evaluate": { "total": 229.04016157183423, "count": 125051, "self": 229.04016157183423 } } }, "workers": { "total": 1.86956924317019, "count": 129393, "self": 0.0, "children": { "worker_root": { "total": 4979.0941547790135, "count": 129393, "is_parallel": true, "self": 1828.8257104030322, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019460849998722551, "count": 1, "is_parallel": true, "self": 0.000589152000429749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013569329994425061, "count": 8, "is_parallel": true, "self": 0.0013569329994425061 } } }, "UnityEnvironment.step": { "total": 0.06023125599995183, "count": 1, "is_parallel": true, "self": 0.0006145440002001124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005822230000376294, "count": 1, "is_parallel": true, "self": 0.0005822230000376294 }, "communicator.exchange": { "total": 0.057012595999822224, "count": 1, "is_parallel": true, "self": 0.057012595999822224 }, "steps_from_proto": { "total": 0.002021892999891861, "count": 1, "is_parallel": true, "self": 0.00039777599931767327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016241170005741878, "count": 8, "is_parallel": true, "self": 0.0016241170005741878 } } } } } } }, "UnityEnvironment.step": { "total": 3150.2684443759813, "count": 129392, "is_parallel": true, "self": 70.87171124777524, "children": { "UnityEnvironment._generate_step_input": { "total": 49.52848356807726, "count": 129392, "is_parallel": true, "self": 49.52848356807726 }, "communicator.exchange": { "total": 2799.1049123709913, "count": 129392, "is_parallel": true, "self": 2799.1049123709913 }, "steps_from_proto": { "total": 230.76333718913747, "count": 129392, "is_parallel": true, "self": 46.685705306220825, "children": { "_process_rank_one_or_two_observation": { "total": 184.07763188291665, "count": 1035136, "is_parallel": true, "self": 184.07763188291665 } } } } } } } } } } }, "trainer_advance": { "total": 1339.498617247028, "count": 129393, "self": 5.908663831080503, "children": { "process_trajectory": { "total": 242.71104529693775, "count": 129393, "self": 242.22114455293786, "children": { "RLTrainer._checkpoint": { "total": 0.4899007439998968, "count": 4, "self": 0.4899007439998968 } } }, "_update_policy": { "total": 1090.8789081190098, "count": 915, "self": 706.5805094140787, "children": { "TorchPPOOptimizer.update": { "total": 384.29839870493106, "count": 45639, "self": 384.29839870493106 } } } } } } }, "trainer_threads": { "total": 1.0100002327817492e-06, "count": 1, "self": 1.0100002327817492e-06 }, "TrainerController._save_models": { "total": 0.11260172600032092, "count": 1, "self": 0.001567603000694362, "children": { "RLTrainer._checkpoint": { "total": 0.11103412299962656, "count": 1, "self": 0.11103412299962656 } } } } } } }