ppo-Pyramids / run_logs /timers.json
WilsonLai's picture
First Push
5020d13 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.42266348004341125,
"min": 0.40645164251327515,
"max": 1.6001043319702148,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4084.619873046875,
"min": 4005.9873046875,
"max": 16385.068359375,
"count": 100
},
"Pyramids.Step.mean": {
"value": 999895.0,
"min": 9984.0,
"max": 999895.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 999895.0,
"min": 9984.0,
"max": 999895.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5359901785850525,
"min": -0.12533265352249146,
"max": 0.544092059135437,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 48.77510452270508,
"min": -10.277276992797852,
"max": 51.1446533203125,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004519105423241854,
"min": -0.016497844830155373,
"max": 0.3738231658935547,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.4112386107444763,
"min": -1.550797462463379,
"max": 29.71672821044922,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0646835458210262,
"min": 0.06147479344702637,
"max": 0.08327887520821625,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.2587341832841048,
"min": 0.12734769352149064,
"max": 0.40026546428756166,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015497061334220536,
"min": 0.0002792507036756795,
"max": 0.020551621527799095,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.061988245336882145,
"min": 0.0007600886183354305,
"max": 0.10275810763899547,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4528495157499996e-06,
"min": 1.4528495157499996e-06,
"max": 0.0002981568006144,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 5.8113980629999985e-06,
"min": 5.8113980629999985e-06,
"max": 0.0012526584824471998,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10048425,
"min": 0.10048425,
"max": 0.1993856,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.401937,
"min": 0.38917120000000005,
"max": 0.9175528000000002,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.8376575000000004e-05,
"min": 5.8376575000000004e-05,
"max": 0.00993862144,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00023350630000000002,
"min": 0.00023350630000000002,
"max": 0.04176352472,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00858924351632595,
"min": 0.008111522532999516,
"max": 0.8777166604995728,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.0343569740653038,
"min": 0.03244609013199806,
"max": 1.7554333209991455,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 408.7857142857143,
"min": 271.2857142857143,
"max": 999.0,
"count": 96
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 11446.0,
"min": 337.0,
"max": 15984.0,
"count": 96
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4483142692063535,
"min": -1.0000000521540642,
"max": 1.7089310237045945,
"count": 96
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 40.5527995377779,
"min": -16.000000834465027,
"max": 51.01219940185547,
"count": 96
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4483142692063535,
"min": -1.0000000521540642,
"max": 1.7089310237045945,
"count": 96
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 40.5527995377779,
"min": -16.000000834465027,
"max": 51.01219940185547,
"count": 96
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.036695394309520325,
"min": 0.027285841380944476,
"max": 9.785773238167167,
"count": 96
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.027471040666569,
"min": 0.4216572344303131,
"max": 156.57237181067467,
"count": 96
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1757500199",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757503462"
},
"total": 3263.1308994749998,
"count": 1,
"self": 1.126393394999468,
"children": {
"run_training.setup": {
"total": 0.03554651000013109,
"count": 1,
"self": 0.03554651000013109
},
"TrainerController.start_learning": {
"total": 3261.96895957,
"count": 1,
"self": 2.2900739629303644,
"children": {
"TrainerController._reset_env": {
"total": 3.383359518999896,
"count": 1,
"self": 3.383359518999896
},
"TrainerController.advance": {
"total": 3256.17461831507,
"count": 63892,
"self": 2.6636268921138253,
"children": {
"env_step": {
"total": 2182.1298822208737,
"count": 63892,
"self": 2019.4075035879132,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.3145471099142,
"count": 63892,
"self": 6.917813840763301,
"children": {
"TorchPolicy.evaluate": {
"total": 154.3967332691509,
"count": 62555,
"self": 154.3967332691509
}
}
},
"workers": {
"total": 1.4078315230462977,
"count": 63892,
"self": 0.0,
"children": {
"worker_root": {
"total": 3252.986740535741,
"count": 63892,
"is_parallel": true,
"self": 1408.4531665957256,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003133062999950198,
"count": 1,
"is_parallel": true,
"self": 0.0011688539998431224,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019642090001070756,
"count": 8,
"is_parallel": true,
"self": 0.0019642090001070756
}
}
},
"UnityEnvironment.step": {
"total": 0.11435396599972592,
"count": 1,
"is_parallel": true,
"self": 0.002692166998713219,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005556200003411504,
"count": 1,
"is_parallel": true,
"self": 0.0005556200003411504
},
"communicator.exchange": {
"total": 0.10907490400040842,
"count": 1,
"is_parallel": true,
"self": 0.10907490400040842
},
"steps_from_proto": {
"total": 0.002031275000263122,
"count": 1,
"is_parallel": true,
"self": 0.000420048999330902,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00161122600093222,
"count": 8,
"is_parallel": true,
"self": 0.00161122600093222
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1844.5335739400152,
"count": 63891,
"is_parallel": true,
"self": 43.917158475002,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 30.538144012094563,
"count": 63891,
"is_parallel": true,
"self": 30.538144012094563
},
"communicator.exchange": {
"total": 1645.4129819659884,
"count": 63891,
"is_parallel": true,
"self": 1645.4129819659884
},
"steps_from_proto": {
"total": 124.6652894869303,
"count": 63891,
"is_parallel": true,
"self": 26.98453693653937,
"children": {
"_process_rank_one_or_two_observation": {
"total": 97.68075255039093,
"count": 511128,
"is_parallel": true,
"self": 97.68075255039093
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1071.3811092020824,
"count": 63892,
"self": 4.364061194014539,
"children": {
"process_trajectory": {
"total": 161.4653533310693,
"count": 63892,
"self": 161.2352164820686,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23013684900070075,
"count": 2,
"self": 0.23013684900070075
}
}
},
"_update_policy": {
"total": 905.5516946769985,
"count": 446,
"self": 354.527959111012,
"children": {
"TorchPPOOptimizer.update": {
"total": 551.0237355659865,
"count": 22785,
"self": 551.0237355659865
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2919999790028669e-06,
"count": 1,
"self": 1.2919999790028669e-06
},
"TrainerController._save_models": {
"total": 0.12090648100002,
"count": 1,
"self": 0.0024706030008019297,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11843587799921806,
"count": 1,
"self": 0.11843587799921806
}
}
}
}
}
}
}