{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5028998851776123, "min": 0.5028998851776123, "max": 1.4695398807525635, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15135.275390625, "min": 15135.275390625, "max": 44579.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989976.0, "min": 29952.0, "max": 989976.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989976.0, "min": 29952.0, "max": 989976.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5349655151367188, "min": -0.11395851522684097, "max": 0.6083133816719055, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.53509521484375, "min": -27.46400260925293, "max": 171.54437255859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03529082611203194, "min": -0.09298340976238251, "max": 0.27694836258888245, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -10.128466606140137, "min": -26.035354614257812, "max": 66.46760559082031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06676488253190144, "min": 0.06487362207362235, "max": 0.07545464212218962, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9347083554466201, "min": 0.4908652668417399, "max": 1.0797000884582908, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017563678713292678, "min": 0.000982761730550074, "max": 0.020494816895137585, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24589150198609747, "min": 0.006879332113850518, "max": 0.30742225342706375, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.461718941364287e-06, "min": 7.461718941364287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010446406517910001, "min": 0.00010446406517910001, "max": 0.0033839021720327004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248720714285717, "min": 0.10248720714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348209000000003, "min": 1.3691136000000002, "max": 2.5279673000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584719935714286, "min": 0.0002584719935714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036186079100000005, "min": 0.0036186079100000005, "max": 0.11282393327000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009342735633254051, "min": 0.009342735633254051, "max": 0.41652894020080566, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13079829514026642, "min": 0.13079829514026642, "max": 2.9157025814056396, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 337.10526315789474, "min": 309.5268817204301, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32025.0, "min": 15984.0, "max": 33191.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5786589303299001, "min": -1.0000000521540642, "max": 1.6474558973825106, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.9725983813405, "min": -32.000001668930054, "max": 153.2133984565735, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5786589303299001, "min": -1.0000000521540642, "max": 1.6474558973825106, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.9725983813405, "min": -32.000001668930054, "max": 153.2133984565735, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03272266578044908, "min": 0.030321995733976766, "max": 8.237760927528143, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1086532491426624, "min": 2.731448870181339, "max": 131.8041748404503, "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": "1743008158", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743010673" }, "total": 2515.1668689410003, "count": 1, "self": 1.095464601000458, "children": { "run_training.setup": { "total": 0.021430106000025262, "count": 1, "self": 0.021430106000025262 }, "TrainerController.start_learning": { "total": 2514.049974234, "count": 1, "self": 1.6639045399379029, "children": { "TrainerController._reset_env": { "total": 2.24141059700014, "count": 1, "self": 2.24141059700014 }, "TrainerController.advance": { "total": 2510.0540116950615, "count": 63877, "self": 1.7006393590127118, "children": { "env_step": { "total": 1774.6063853939613, "count": 63877, "self": 1594.6898395009825, "children": { "SubprocessEnvManager._take_step": { "total": 178.9736997569862, "count": 63877, "self": 5.322926828024265, "children": { "TorchPolicy.evaluate": { "total": 173.65077292896194, "count": 62564, "self": 173.65077292896194 } } }, "workers": { "total": 0.9428461359925677, "count": 63877, "self": 0.0, "children": { "worker_root": { "total": 2507.982096880023, "count": 63877, "is_parallel": true, "self": 1044.1173434320544, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022396250001293083, "count": 1, "is_parallel": true, "self": 0.0007497599999624072, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014898650001669012, "count": 8, "is_parallel": true, "self": 0.0014898650001669012 } } }, "UnityEnvironment.step": { "total": 0.08175451300030545, "count": 1, "is_parallel": true, "self": 0.0005850680008734344, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004889319998255814, "count": 1, "is_parallel": true, "self": 0.0004889319998255814 }, "communicator.exchange": { "total": 0.07890167199957432, "count": 1, "is_parallel": true, "self": 0.07890167199957432 }, "steps_from_proto": { "total": 0.0017788410000321164, "count": 1, "is_parallel": true, "self": 0.00038208900014069513, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013967519998914213, "count": 8, "is_parallel": true, "self": 0.0013967519998914213 } } } } } } }, "UnityEnvironment.step": { "total": 1463.8647534479687, "count": 63876, "is_parallel": true, "self": 34.940529567028534, "children": { "UnityEnvironment._generate_step_input": { "total": 26.05742025501422, "count": 63876, "is_parallel": true, "self": 26.05742025501422 }, "communicator.exchange": { "total": 1292.2112105988667, "count": 63876, "is_parallel": true, "self": 1292.2112105988667 }, "steps_from_proto": { "total": 110.65559302705924, "count": 63876, "is_parallel": true, "self": 23.39903664608846, "children": { "_process_rank_one_or_two_observation": { "total": 87.25655638097078, "count": 511008, "is_parallel": true, "self": 87.25655638097078 } } } } } } } } } } }, "trainer_advance": { "total": 733.7469869420875, "count": 63877, "self": 3.111699749138097, "children": { "process_trajectory": { "total": 142.0162464699588, "count": 63877, "self": 141.79468117495844, "children": { "RLTrainer._checkpoint": { "total": 0.22156529500034594, "count": 2, "self": 0.22156529500034594 } } }, "_update_policy": { "total": 588.6190407229906, "count": 448, "self": 325.28446773401447, "children": { "TorchPPOOptimizer.update": { "total": 263.3345729889761, "count": 22815, "self": 263.3345729889761 } } } } } } }, "trainer_threads": { "total": 1.1590000212891027e-06, "count": 1, "self": 1.1590000212891027e-06 }, "TrainerController._save_models": { "total": 0.0906462430002648, "count": 1, "self": 0.0013437540001177695, "children": { "RLTrainer._checkpoint": { "total": 0.08930248900014703, "count": 1, "self": 0.08930248900014703 } } } } } } }