{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3234502077102661, "min": 0.32301390171051025, "max": 1.4400469064712524, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9600.001953125, "min": 9600.001953125, "max": 43685.26171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.551596462726593, "min": -0.09532348066568375, "max": 0.5731770992279053, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.44700622558594, "min": -22.877635955810547, "max": 159.91641235351562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05366688221693039, "min": 0.012212755158543587, "max": 0.4041997790336609, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.026726722717285, "min": 3.0287632942199707, "max": 95.79534912109375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06645435084207624, "min": 0.06543215284562316, "max": 0.0722261587936856, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9968152626311435, "min": 0.49824292056902103, "max": 1.0612249622365697, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016585891865447976, "min": 0.00038675618254793004, "max": 0.017439287193285833, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24878837798171966, "min": 0.00541458655567102, "max": 0.24878837798171966, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.54567748480667e-06, "min": 7.54567748480667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011318516227210005, "min": 0.00011318516227210005, "max": 0.0035071598309468, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251519333333334, "min": 0.10251519333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377279000000001, "min": 1.3691136000000002, "max": 2.5690532, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002612678140000001, "min": 0.0002612678140000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003919017210000001, "min": 0.003919017210000001, "max": 0.11692841468000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01329939253628254, "min": 0.013048590160906315, "max": 0.4217536449432373, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19949088990688324, "min": 0.18268026411533356, "max": 2.952275514602661, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.2967032967033, "min": 313.6043956043956, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29966.0, "min": 15984.0, "max": 32421.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5168153637876878, "min": -1.0000000521540642, "max": 1.6424263590476016, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.03019810467958, "min": -32.000001668930054, "max": 149.46079867333174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5168153637876878, "min": -1.0000000521540642, "max": 1.6424263590476016, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.03019810467958, "min": -32.000001668930054, "max": 149.46079867333174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.045219409689537485, "min": 0.042431707330211836, "max": 8.877920700237155, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.114966281747911, "min": 3.861285367049277, "max": 142.04673120379448, "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": "1714069439", "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": "1714071572" }, "total": 2132.608589376, "count": 1, "self": 0.4769928420000724, "children": { "run_training.setup": { "total": 0.048791671000117276, "count": 1, "self": 0.048791671000117276 }, "TrainerController.start_learning": { "total": 2132.082804863, "count": 1, "self": 1.28648098296253, "children": { "TrainerController._reset_env": { "total": 2.0972978690001582, "count": 1, "self": 2.0972978690001582 }, "TrainerController.advance": { "total": 2128.6152456560376, "count": 63857, "self": 1.312738692146013, "children": { "env_step": { "total": 1519.1494084269184, "count": 63857, "self": 1394.6666045448844, "children": { "SubprocessEnvManager._take_step": { "total": 123.69512062697504, "count": 63857, "self": 4.358122484072055, "children": { "TorchPolicy.evaluate": { "total": 119.33699814290298, "count": 62569, "self": 119.33699814290298 } } }, "workers": { "total": 0.787683255058937, "count": 63857, "self": 0.0, "children": { "worker_root": { "total": 2126.9572456410447, "count": 63857, "is_parallel": true, "self": 847.7118789470296, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002121635999856153, "count": 1, "is_parallel": true, "self": 0.000606754000273213, "children": { "_process_rank_one_or_two_observation": { "total": 0.00151488199958294, "count": 8, "is_parallel": true, "self": 0.00151488199958294 } } }, "UnityEnvironment.step": { "total": 0.0478811229997973, "count": 1, "is_parallel": true, "self": 0.0006120299997292022, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005112320000080217, "count": 1, "is_parallel": true, "self": 0.0005112320000080217 }, "communicator.exchange": { "total": 0.04515043600008539, "count": 1, "is_parallel": true, "self": 0.04515043600008539 }, "steps_from_proto": { "total": 0.0016074249999746826, "count": 1, "is_parallel": true, "self": 0.00033410800028832455, "children": { "_process_rank_one_or_two_observation": { "total": 0.001273316999686358, "count": 8, "is_parallel": true, "self": 0.001273316999686358 } } } } } } }, "UnityEnvironment.step": { "total": 1279.245366694015, "count": 63856, "is_parallel": true, "self": 33.284108818991854, "children": { "UnityEnvironment._generate_step_input": { "total": 22.511942109969596, "count": 63856, "is_parallel": true, "self": 22.511942109969596 }, "communicator.exchange": { "total": 1127.5366388020002, "count": 63856, "is_parallel": true, "self": 1127.5366388020002 }, "steps_from_proto": { "total": 95.9126769630534, "count": 63856, "is_parallel": true, "self": 19.08276625528356, "children": { "_process_rank_one_or_two_observation": { "total": 76.82991070776984, "count": 510848, "is_parallel": true, "self": 76.82991070776984 } } } } } } } } } } }, "trainer_advance": { "total": 608.153098536973, "count": 63857, "self": 2.4908433079874612, "children": { "process_trajectory": { "total": 122.89451545797965, "count": 63857, "self": 122.70947350697952, "children": { "RLTrainer._checkpoint": { "total": 0.1850419510001302, "count": 2, "self": 0.1850419510001302 } } }, "_update_policy": { "total": 482.76773977100584, "count": 445, "self": 283.9731238930158, "children": { "TorchPPOOptimizer.update": { "total": 198.79461587799005, "count": 22785, "self": 198.79461587799005 } } } } } } }, "trainer_threads": { "total": 8.150000212481245e-07, "count": 1, "self": 8.150000212481245e-07 }, "TrainerController._save_models": { "total": 0.08377953999979582, "count": 1, "self": 0.0012994310000067344, "children": { "RLTrainer._checkpoint": { "total": 0.08248010899978908, "count": 1, "self": 0.08248010899978908 } } } } } } }