ppo-Huggy / run_logs /timers.json
schase2's picture
Huggy
718a336 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070401191711426,
"min": 1.4070401191711426,
"max": 1.4249258041381836,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68462.3515625,
"min": 68167.453125,
"max": 75649.375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.75951903807615,
"min": 95.3102119460501,
"max": 415.8333333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49780.0,
"min": 49240.0,
"max": 50293.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999572.0,
"min": 49338.0,
"max": 1999572.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999572.0,
"min": 49338.0,
"max": 1999572.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.325732469558716,
"min": 0.06255882233381271,
"max": 2.3539774417877197,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1160.54052734375,
"min": 7.444499492645264,
"max": 1191.9246826171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5443414596613043,
"min": 1.829728446587795,
"max": 3.836275418819715,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1768.6263883709908,
"min": 217.7376851439476,
"max": 1884.2324231863022,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5443414596613043,
"min": 1.829728446587795,
"max": 3.836275418819715,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1768.6263883709908,
"min": 217.7376851439476,
"max": 1884.2324231863022,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016459789783402814,
"min": 0.012514883282064048,
"max": 0.021028355627155784,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04937936935020844,
"min": 0.027850229739366718,
"max": 0.05635005068033934,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04913059626188543,
"min": 0.022621144354343415,
"max": 0.05839915850924121,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14739178878565629,
"min": 0.04524228870868683,
"max": 0.17519747552772363,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3905988698333396e-06,
"min": 3.3905988698333396e-06,
"max": 0.000295368376543875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0171796609500018e-05,
"min": 1.0171796609500018e-05,
"max": 0.0008441839686053499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113016666666667,
"min": 0.10113016666666667,
"max": 0.19845612499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033905,
"min": 0.20739595,
"max": 0.5813946499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.63953166666668e-05,
"min": 6.63953166666668e-05,
"max": 0.004922960637500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019918595000000038,
"min": 0.00019918595000000038,
"max": 0.014071593035000003,
"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": "1732642113",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732644467"
},
"total": 2354.950804011,
"count": 1,
"self": 0.42586634400004186,
"children": {
"run_training.setup": {
"total": 0.06662607299995216,
"count": 1,
"self": 0.06662607299995216
},
"TrainerController.start_learning": {
"total": 2354.458311594,
"count": 1,
"self": 4.262083654992239,
"children": {
"TrainerController._reset_env": {
"total": 5.863396821000038,
"count": 1,
"self": 5.863396821000038
},
"TrainerController.advance": {
"total": 2344.221016678008,
"count": 230963,
"self": 4.247956317941771,
"children": {
"env_step": {
"total": 1860.2222075480058,
"count": 230963,
"self": 1457.6637749180375,
"children": {
"SubprocessEnvManager._take_step": {
"total": 399.81901557200183,
"count": 230963,
"self": 15.369798736997609,
"children": {
"TorchPolicy.evaluate": {
"total": 384.4492168350042,
"count": 222828,
"self": 384.4492168350042
}
}
},
"workers": {
"total": 2.7394170579665342,
"count": 230963,
"self": 0.0,
"children": {
"worker_root": {
"total": 2347.3505954530146,
"count": 230963,
"is_parallel": true,
"self": 1162.9495211239964,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008031959999925675,
"count": 1,
"is_parallel": true,
"self": 0.0002177800000708885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000585415999921679,
"count": 2,
"is_parallel": true,
"self": 0.000585415999921679
}
}
},
"UnityEnvironment.step": {
"total": 0.028669761000060134,
"count": 1,
"is_parallel": true,
"self": 0.000342870000054063,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001981970000315414,
"count": 1,
"is_parallel": true,
"self": 0.0001981970000315414
},
"communicator.exchange": {
"total": 0.027373026999953254,
"count": 1,
"is_parallel": true,
"self": 0.027373026999953254
},
"steps_from_proto": {
"total": 0.0007556670000212762,
"count": 1,
"is_parallel": true,
"self": 0.0002009080000107133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005547590000105629,
"count": 2,
"is_parallel": true,
"self": 0.0005547590000105629
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1184.4010743290182,
"count": 230962,
"is_parallel": true,
"self": 36.51696684996159,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.33265633006317,
"count": 230962,
"is_parallel": true,
"self": 79.33265633006317
},
"communicator.exchange": {
"total": 982.6531139159994,
"count": 230962,
"is_parallel": true,
"self": 982.6531139159994
},
"steps_from_proto": {
"total": 85.89833723299387,
"count": 230962,
"is_parallel": true,
"self": 30.489920559858774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.40841667313509,
"count": 461924,
"is_parallel": true,
"self": 55.40841667313509
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 479.7508528120603,
"count": 230963,
"self": 6.425084881050452,
"children": {
"process_trajectory": {
"total": 154.44866158400953,
"count": 230963,
"self": 152.95501910400935,
"children": {
"RLTrainer._checkpoint": {
"total": 1.493642480000176,
"count": 10,
"self": 1.493642480000176
}
}
},
"_update_policy": {
"total": 318.87710634700034,
"count": 97,
"self": 254.22816536400842,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.64894098299192,
"count": 2910,
"self": 64.64894098299192
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.014999725157395e-06,
"count": 1,
"self": 1.014999725157395e-06
},
"TrainerController._save_models": {
"total": 0.11181342500003666,
"count": 1,
"self": 0.0021210059999248188,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10969241900011184,
"count": 1,
"self": 0.10969241900011184
}
}
}
}
}
}
}