ppo-Huggy / run_logs /timers.json
dgrachev's picture
Huggy
d7a43ad verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4034286737442017,
"min": 1.4034286737442017,
"max": 1.4254872798919678,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69313.9375,
"min": 68438.953125,
"max": 75757.6484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.03434343434344,
"min": 84.78559176672384,
"max": 401.064,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49517.0,
"min": 48862.0,
"max": 50133.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999966.0,
"min": 49508.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999966.0,
"min": 49508.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3300395011901855,
"min": 0.15231294929981232,
"max": 2.444532871246338,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1153.3695068359375,
"min": 18.88680648803711,
"max": 1416.223876953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.547280105436691,
"min": 1.6721691631021038,
"max": 3.989206239933104,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1755.903652191162,
"min": 207.34897622466087,
"max": 2265.795148730278,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.547280105436691,
"min": 1.6721691631021038,
"max": 3.989206239933104,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1755.903652191162,
"min": 207.34897622466087,
"max": 2265.795148730278,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01615975612949114,
"min": 0.0126582127319125,
"max": 0.020576139347879992,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048479268388473426,
"min": 0.025316425463825,
"max": 0.05574235321061376,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0509031286256181,
"min": 0.022267151655008394,
"max": 0.06289702306191126,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1527093858768543,
"min": 0.04453430331001679,
"max": 0.1620153971016407,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.302298899266655e-06,
"min": 3.302298899266655e-06,
"max": 0.00029532607655797496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.906896697799964e-06,
"min": 9.906896697799964e-06,
"max": 0.0008441017686327499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110073333333335,
"min": 0.10110073333333335,
"max": 0.19844202499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033022,
"min": 0.20733049999999997,
"max": 0.5813672500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.492659333333314e-05,
"min": 6.492659333333314e-05,
"max": 0.0049222570475,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019477977999999944,
"min": 0.00019477977999999944,
"max": 0.014070225775,
"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": "1716290583",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716292959"
},
"total": 2375.667683318,
"count": 1,
"self": 0.7660055989999819,
"children": {
"run_training.setup": {
"total": 0.08359398400000373,
"count": 1,
"self": 0.08359398400000373
},
"TrainerController.start_learning": {
"total": 2374.818083735,
"count": 1,
"self": 4.221452210004372,
"children": {
"TrainerController._reset_env": {
"total": 3.3173688159999983,
"count": 1,
"self": 3.3173688159999983
},
"TrainerController.advance": {
"total": 2367.1017139189958,
"count": 232223,
"self": 4.626336203976734,
"children": {
"env_step": {
"total": 1874.9337643770623,
"count": 232223,
"self": 1549.068361579129,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.1008987769725,
"count": 232223,
"self": 16.39642671596198,
"children": {
"TorchPolicy.evaluate": {
"total": 306.7044720610105,
"count": 222996,
"self": 306.7044720610105
}
}
},
"workers": {
"total": 2.7645040209607146,
"count": 232223,
"self": 0.0,
"children": {
"worker_root": {
"total": 2367.4096484141073,
"count": 232223,
"is_parallel": true,
"self": 1123.8084721810542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011470099999542072,
"count": 1,
"is_parallel": true,
"self": 0.00034140499991508477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008056050000391224,
"count": 2,
"is_parallel": true,
"self": 0.0008056050000391224
}
}
},
"UnityEnvironment.step": {
"total": 0.029489429000022938,
"count": 1,
"is_parallel": true,
"self": 0.0004093860000580207,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019686199999568998,
"count": 1,
"is_parallel": true,
"self": 0.00019686199999568998
},
"communicator.exchange": {
"total": 0.02814195399997743,
"count": 1,
"is_parallel": true,
"self": 0.02814195399997743
},
"steps_from_proto": {
"total": 0.0007412269999917953,
"count": 1,
"is_parallel": true,
"self": 0.00021432199997661883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005269050000151765,
"count": 2,
"is_parallel": true,
"self": 0.0005269050000151765
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1243.6011762330531,
"count": 232222,
"is_parallel": true,
"self": 38.940432776992566,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.17092032309324,
"count": 232222,
"is_parallel": true,
"self": 80.17092032309324
},
"communicator.exchange": {
"total": 1036.3701030269706,
"count": 232222,
"is_parallel": true,
"self": 1036.3701030269706
},
"steps_from_proto": {
"total": 88.1197201059968,
"count": 232222,
"is_parallel": true,
"self": 31.2259999128878,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.893720193109004,
"count": 464444,
"is_parallel": true,
"self": 56.893720193109004
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.5416133379569,
"count": 232223,
"self": 6.369612237976128,
"children": {
"process_trajectory": {
"total": 151.57336507598183,
"count": 232223,
"self": 149.8533336899813,
"children": {
"RLTrainer._checkpoint": {
"total": 1.720031386000528,
"count": 10,
"self": 1.720031386000528
}
}
},
"_update_policy": {
"total": 329.59863602399895,
"count": 97,
"self": 266.0424769739963,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.556159050002634,
"count": 2910,
"self": 63.556159050002634
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3690000741917174e-06,
"count": 1,
"self": 1.3690000741917174e-06
},
"TrainerController._save_models": {
"total": 0.17754742099987197,
"count": 1,
"self": 0.0029895180000494292,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17455790299982255,
"count": 1,
"self": 0.17455790299982255
}
}
}
}
}
}
}