{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9104369282722473, "min": 0.9104369282722473, "max": 1.4950510263442993, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 27269.40625, "min": 27269.40625, "max": 45353.8671875, "count": 3 }, "Pyramids.Step.mean": { "value": 89938.0, "min": 29960.0, "max": 89938.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89938.0, "min": 29960.0, "max": 89938.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07978370785713196, "min": -0.07978370785713196, "max": 0.011218065395951271, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.148090362548828, "min": -19.148090362548828, "max": 2.6698994636535645, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.13221655786037445, "min": 0.13221655786037445, "max": 0.22668828070163727, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 31.731975555419922, "min": 31.731975555419922, "max": 54.631874084472656, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06983599036424905, "min": 0.06801218492045276, "max": 0.06983599036424905, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7681958940067395, "min": 0.4760852944431693, "max": 0.7681958940067395, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00028580750626034567, "min": 0.00028580750626034567, "max": 0.003454588409511801, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0031438825688638026, "min": 0.0031438825688638026, "max": 0.02438344863103822, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.769298319327273e-05, "min": 7.769298319327273e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000854622815126, "min": 0.000854622815126, "max": 0.0018258784913739998, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12589763636363638, "min": 0.12589763636363638, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3848740000000002, "min": 1.2868480000000002, "max": 1.708626, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.002597173872727273, "min": 0.002597173872727273, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.028568912600000003, "min": 0.028568912600000003, "max": 0.0609117374, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.09547004848718643, "min": 0.09547004848718643, "max": 0.31422263383865356, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.0501705408096313, "min": 1.0501705408096313, "max": 2.1995584964752197, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 985.3125, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31968.0, "min": 16759.0, "max": 31968.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9999250518158078, "min": -0.9999250518158078, "max": -0.8691176964956171, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -31.99760165810585, "min": -31.99760165810585, "max": -14.775000840425491, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9999250518158078, "min": -0.9999250518158078, "max": -0.8691176964956171, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -31.99760165810585, "min": -31.99760165810585, "max": -14.775000840425491, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.1075334046036005, "min": 1.1075334046036005, "max": 6.120552830617218, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 35.441068947315216, "min": 35.441068947315216, "max": 104.0493981204927, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1738678798", "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=PyramidsTraining --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": "1738678990" }, "total": 192.37076133999994, "count": 1, "self": 0.47772477999978946, "children": { "run_training.setup": { "total": 0.019454280999980256, "count": 1, "self": 0.019454280999980256 }, "TrainerController.start_learning": { "total": 191.87358227900017, "count": 1, "self": 0.1268479760003629, "children": { "TrainerController._reset_env": { "total": 2.185611063000124, "count": 1, "self": 2.185611063000124 }, "TrainerController.advance": { "total": 189.4479347519998, "count": 6309, "self": 0.12849428701770194, "children": { "env_step": { "total": 123.14227308699128, "count": 6309, "self": 107.65577049999797, "children": { "SubprocessEnvManager._take_step": { "total": 15.416029276010931, "count": 6309, "self": 0.45713673900922913, "children": { "TorchPolicy.evaluate": { "total": 14.958892537001702, "count": 6299, "self": 14.958892537001702 } } }, "workers": { "total": 0.07047331098237919, "count": 6309, "self": 0.0, "children": { "worker_root": { "total": 191.3320006450126, "count": 6309, "is_parallel": true, "self": 94.17233583800476, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019803870000032475, "count": 1, "is_parallel": true, "self": 0.0006489289994533465, "children": { "_process_rank_one_or_two_observation": { "total": 0.001331458000549901, "count": 8, "is_parallel": true, "self": 0.001331458000549901 } } }, "UnityEnvironment.step": { "total": 0.04668351899999834, "count": 1, "is_parallel": true, "self": 0.0005366660002437129, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005834959999901912, "count": 1, "is_parallel": true, "self": 0.0005834959999901912 }, "communicator.exchange": { "total": 0.044018868999955885, "count": 1, "is_parallel": true, "self": 0.044018868999955885 }, "steps_from_proto": { "total": 0.0015444879998085526, "count": 1, "is_parallel": true, "self": 0.00032092499964164745, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012235630001669051, "count": 8, "is_parallel": true, "self": 0.0012235630001669051 } } } } } } }, "UnityEnvironment.step": { "total": 97.15966480700786, "count": 6308, "is_parallel": true, "self": 3.0712249569940013, "children": { "UnityEnvironment._generate_step_input": { "total": 2.2637352109989024, "count": 6308, "is_parallel": true, "self": 2.2637352109989024 }, "communicator.exchange": { "total": 82.75593668700435, "count": 6308, "is_parallel": true, "self": 82.75593668700435 }, "steps_from_proto": { "total": 9.068767952010603, "count": 6308, "is_parallel": true, "self": 1.7745969419788707, "children": { "_process_rank_one_or_two_observation": { "total": 7.294171010031732, "count": 50464, "is_parallel": true, "self": 7.294171010031732 } } } } } } } } } } }, "trainer_advance": { "total": 66.17716737799083, "count": 6309, "self": 0.1597476449910573, "children": { "process_trajectory": { "total": 11.530082399000094, "count": 6309, "self": 11.530082399000094 }, "_update_policy": { "total": 54.487337333999676, "count": 33, "self": 30.197526046996018, "children": { "TorchPPOOptimizer.update": { "total": 24.28981128700366, "count": 2271, "self": 24.28981128700366 } } } } } } }, "trainer_threads": { "total": 9.51999936660286e-07, "count": 1, "self": 9.51999936660286e-07 }, "TrainerController._save_models": { "total": 0.11318753599994125, "count": 1, "self": 0.0013856269999905635, "children": { "RLTrainer._checkpoint": { "total": 0.11180190899995068, "count": 1, "self": 0.11180190899995068 } } } } } } }