ppo-Huggy / run_logs /timers.json
yoimisan's picture
Huggy
9670896 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4067282676696777,
"min": 1.4067282676696777,
"max": 1.4267104864120483,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68517.515625,
"min": 68245.203125,
"max": 74527.3515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 120.00966183574879,
"min": 94.07794676806084,
"max": 403.06451612903226,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49684.0,
"min": 48856.0,
"max": 50173.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999377.0,
"min": 49741.0,
"max": 1999377.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999377.0,
"min": 49741.0,
"max": 1999377.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.237546682357788,
"min": 0.09607413411140442,
"max": 2.3809056282043457,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 926.3443603515625,
"min": 11.817118644714355,
"max": 1248.061767578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.378910083125755,
"min": 1.8053892206370346,
"max": 3.949417063823113,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1398.8687744140625,
"min": 222.06287413835526,
"max": 2015.1901710033417,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.378910083125755,
"min": 1.8053892206370346,
"max": 3.949417063823113,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1398.8687744140625,
"min": 222.06287413835526,
"max": 2015.1901710033417,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013283828423360924,
"min": 0.013242133455666286,
"max": 0.02138835308724083,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.026567656846721847,
"min": 0.02648426691133257,
"max": 0.0577016908316485,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04097425416111947,
"min": 0.023164193663332198,
"max": 0.056895882512132324,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08194850832223893,
"min": 0.046916009734074275,
"max": 0.17068764753639698,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.494023502025003e-06,
"min": 4.494023502025003e-06,
"max": 0.0002953131015622999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.988047004050006e-06,
"min": 8.988047004050006e-06,
"max": 0.0008439991686669499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10149797500000002,
"min": 0.10149797500000002,
"max": 0.1984377,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20299595000000004,
"min": 0.20299595000000004,
"max": 0.5813330500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.474895250000007e-05,
"min": 8.474895250000007e-05,
"max": 0.0049220412299999985,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016949790500000013,
"min": 0.00016949790500000013,
"max": 0.014068519194999999,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1746162577",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1746165027"
},
"total": 2450.3557558130005,
"count": 1,
"self": 0.7993235220001225,
"children": {
"run_training.setup": {
"total": 0.022915539999985413,
"count": 1,
"self": 0.022915539999985413
},
"TrainerController.start_learning": {
"total": 2449.533516751,
"count": 1,
"self": 4.3826136971438245,
"children": {
"TrainerController._reset_env": {
"total": 3.451914321000004,
"count": 1,
"self": 3.451914321000004
},
"TrainerController.advance": {
"total": 2441.541882700856,
"count": 230768,
"self": 4.910912158723477,
"children": {
"env_step": {
"total": 1970.200815735114,
"count": 230768,
"self": 1543.4794984190803,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.9775612800436,
"count": 230768,
"self": 16.27111386111983,
"children": {
"TorchPolicy.evaluate": {
"total": 407.70644741892374,
"count": 222927,
"self": 407.70644741892374
}
}
},
"workers": {
"total": 2.7437560359901454,
"count": 230768,
"self": 0.0,
"children": {
"worker_root": {
"total": 2442.048287661204,
"count": 230768,
"is_parallel": true,
"self": 1185.0274078100542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000822924999965835,
"count": 1,
"is_parallel": true,
"self": 0.00022850799996376736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005944170000020677,
"count": 2,
"is_parallel": true,
"self": 0.0005944170000020677
}
}
},
"UnityEnvironment.step": {
"total": 0.06891200400013986,
"count": 1,
"is_parallel": true,
"self": 0.00036001600005874934,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001973820001239801,
"count": 1,
"is_parallel": true,
"self": 0.0001973820001239801
},
"communicator.exchange": {
"total": 0.0676154889999907,
"count": 1,
"is_parallel": true,
"self": 0.0676154889999907
},
"steps_from_proto": {
"total": 0.0007391169999664271,
"count": 1,
"is_parallel": true,
"self": 0.00020528499976535386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005338320002010732,
"count": 2,
"is_parallel": true,
"self": 0.0005338320002010732
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1257.0208798511499,
"count": 230767,
"is_parallel": true,
"self": 37.38503982528164,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.27628592577094,
"count": 230767,
"is_parallel": true,
"self": 84.27628592577094
},
"communicator.exchange": {
"total": 1046.9668041130108,
"count": 230767,
"is_parallel": true,
"self": 1046.9668041130108
},
"steps_from_proto": {
"total": 88.39274998708652,
"count": 230767,
"is_parallel": true,
"self": 32.890223145208665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.50252684187785,
"count": 461534,
"is_parallel": true,
"self": 55.50252684187785
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 466.4301548070184,
"count": 230768,
"self": 6.795234259906238,
"children": {
"process_trajectory": {
"total": 156.6820366911113,
"count": 230768,
"self": 155.41524141511013,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2667952760011758,
"count": 10,
"self": 1.2667952760011758
}
}
},
"_update_policy": {
"total": 302.9528838560009,
"count": 96,
"self": 239.11099444298316,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.841889413017725,
"count": 2880,
"self": 63.841889413017725
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1629999789875e-06,
"count": 1,
"self": 1.1629999789875e-06
},
"TrainerController._save_models": {
"total": 0.1571048690002499,
"count": 1,
"self": 0.0027012509999622125,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15440361800028768,
"count": 1,
"self": 0.15440361800028768
}
}
}
}
}
}
}