ppo-Pyramids / run_logs /timers.json
hungtran0509's picture
First Push
c4dbe90 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.0881083011627197,
"min": 0.8809857964515686,
"max": 1.453059434890747,
"count": 7
},
"Pyramids.Policy.Entropy.sum": {
"value": 32921.8046875,
"min": 26387.287109375,
"max": 44080.01171875,
"count": 7
},
"Pyramids.Step.mean": {
"value": 209882.0,
"min": 29952.0,
"max": 209882.0,
"count": 7
},
"Pyramids.Step.sum": {
"value": 209882.0,
"min": 29952.0,
"max": 209882.0,
"count": 7
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.06918653100728989,
"min": -0.09390904754400253,
"max": 0.15874703228473663,
"count": 7
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -16.604766845703125,
"min": -22.725990295410156,
"max": 37.623046875,
"count": 7
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0740058496594429,
"min": 0.0740058496594429,
"max": 0.5451943278312683,
"count": 7
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 17.761404037475586,
"min": 17.761404037475586,
"max": 129.2110595703125,
"count": 7
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0689444018778687,
"min": 0.06788426725790177,
"max": 0.07299461602860736,
"count": 7
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9652216262901618,
"min": 0.4751898708053124,
"max": 0.981642822940658,
"count": 7
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.002093444957746351,
"min": 0.0013910636123742816,
"max": 0.009019113559870987,
"count": 7
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.02930822940844891,
"min": 0.009737445286619972,
"max": 0.0631337949190969,
"count": 7
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.0002804460208037095,
"min": 0.0002804460208037095,
"max": 0.00029838354339596195,
"count": 7
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.003926244291251933,
"min": 0.0020691136102954665,
"max": 0.0039694965768345,
"count": 7
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.19348200476190477,
"min": 0.19348200476190477,
"max": 0.19946118095238097,
"count": 7
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.708748066666667,
"min": 1.3897045333333333,
"max": 2.7231655000000003,
"count": 7
},
"Pyramids.Policy.Beta.mean": {
"value": 0.009348852275714288,
"min": 0.009348852275714288,
"max": 0.009946171977142856,
"count": 7
},
"Pyramids.Policy.Beta.sum": {
"value": 0.13088393186000002,
"min": 0.06897148288,
"max": 0.13232423345,
"count": 7
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.05801807716488838,
"min": 0.05801807716488838,
"max": 0.4771438241004944,
"count": 7
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.8122530579566956,
"min": 0.8122530579566956,
"max": 3.3400068283081055,
"count": 7
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 951.483870967742,
"min": 899.3428571428572,
"max": 999.0,
"count": 7
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29496.0,
"min": 15984.0,
"max": 32102.0,
"count": 7
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.7661625470500439,
"min": -1.0000000521540642,
"max": -0.6144057608076504,
"count": 7
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -24.517201505601406,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 7
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.7661625470500439,
"min": -1.0000000521540642,
"max": -0.6144057608076504,
"count": 7
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -24.517201505601406,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 7
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.5831545917317271,
"min": 0.5831545917317271,
"max": 9.840466050431132,
"count": 7
},
"Pyramids.Policy.RndReward.sum": {
"value": 18.660946935415268,
"min": 18.660946935415268,
"max": 157.44745680689812,
"count": 7
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 7
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 7
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1746330554",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746331041"
},
"total": 487.1946583030001,
"count": 1,
"self": 0.2896121310001263,
"children": {
"run_training.setup": {
"total": 0.020723382000028323,
"count": 1,
"self": 0.020723382000028323
},
"TrainerController.start_learning": {
"total": 486.88432278999994,
"count": 1,
"self": 0.3306600939894224,
"children": {
"TrainerController._reset_env": {
"total": 2.3213227620000225,
"count": 1,
"self": 2.3213227620000225
},
"TrainerController.advance": {
"total": 484.0381067170106,
"count": 14382,
"self": 0.35375840499511924,
"children": {
"env_step": {
"total": 328.0226088280084,
"count": 14382,
"self": 289.9520713070226,
"children": {
"SubprocessEnvManager._take_step": {
"total": 37.87847615599196,
"count": 14382,
"self": 1.1544317330012746,
"children": {
"TorchPolicy.evaluate": {
"total": 36.72404442299069,
"count": 14322,
"self": 36.72404442299069
}
}
},
"workers": {
"total": 0.1920613649938332,
"count": 14381,
"self": 0.0,
"children": {
"worker_root": {
"total": 485.5656655980109,
"count": 14381,
"is_parallel": true,
"self": 223.14475308802548,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021114740000029997,
"count": 1,
"is_parallel": true,
"self": 0.0006647980001162068,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014466759998867929,
"count": 8,
"is_parallel": true,
"self": 0.0014466759998867929
}
}
},
"UnityEnvironment.step": {
"total": 0.05251829999997426,
"count": 1,
"is_parallel": true,
"self": 0.0005817040000692941,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000506829999949332,
"count": 1,
"is_parallel": true,
"self": 0.000506829999949332
},
"communicator.exchange": {
"total": 0.04965115299989975,
"count": 1,
"is_parallel": true,
"self": 0.04965115299989975
},
"steps_from_proto": {
"total": 0.0017786130000558842,
"count": 1,
"is_parallel": true,
"self": 0.00037577300008706516,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001402839999968819,
"count": 8,
"is_parallel": true,
"self": 0.001402839999968819
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 262.42091250998544,
"count": 14380,
"is_parallel": true,
"self": 7.620930722998992,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.660667464994958,
"count": 14380,
"is_parallel": true,
"self": 5.660667464994958
},
"communicator.exchange": {
"total": 225.39299888699668,
"count": 14380,
"is_parallel": true,
"self": 225.39299888699668
},
"steps_from_proto": {
"total": 23.746315434994813,
"count": 14380,
"is_parallel": true,
"self": 4.855606864015044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.89070857097977,
"count": 115040,
"is_parallel": true,
"self": 18.89070857097977
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 155.66173948400706,
"count": 14381,
"self": 0.49883766499692683,
"children": {
"process_trajectory": {
"total": 30.0703016630099,
"count": 14381,
"self": 30.0703016630099
},
"_update_policy": {
"total": 125.09260015600023,
"count": 87,
"self": 69.72707509700115,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.36552505899908,
"count": 5217,
"self": 55.36552505899908
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2420000530255493e-06,
"count": 1,
"self": 1.2420000530255493e-06
},
"TrainerController._save_models": {
"total": 0.194231974999866,
"count": 1,
"self": 0.0018597709997720813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19237220400009392,
"count": 1,
"self": 0.19237220400009392
}
}
}
}
}
}
}