ppoHuggy / run_logs /timers.json
Venkat-Shadeslayer's picture
Huggy
ebbc6fe verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4111214876174927,
"min": 1.4111214876174927,
"max": 1.4275734424591064,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69918.25,
"min": 69140.6953125,
"max": 75826.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.97425742574258,
"min": 87.93783303730018,
"max": 442.11504424778764,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49477.0,
"min": 49205.0,
"max": 49959.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999976.0,
"min": 49460.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999976.0,
"min": 49460.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.376939535140991,
"min": 0.08531327545642853,
"max": 2.4145843982696533,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1200.3544921875,
"min": 9.555087089538574,
"max": 1310.443115234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.717684712150309,
"min": 1.759443382333432,
"max": 3.855523490597841,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1877.4307796359062,
"min": 197.05765882134438,
"max": 2089.69373190403,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.717684712150309,
"min": 1.759443382333432,
"max": 3.855523490597841,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1877.4307796359062,
"min": 197.05765882134438,
"max": 2089.69373190403,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.020013542662814465,
"min": 0.012913322693202644,
"max": 0.020860696900732972,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.060040627988443396,
"min": 0.02582664538640529,
"max": 0.060040627988443396,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049714988966782885,
"min": 0.02241721022874117,
"max": 0.054091395686070125,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14914496690034865,
"min": 0.04612717963755131,
"max": 0.1543457226206859,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.107448964216664e-06,
"min": 3.107448964216664e-06,
"max": 0.0002952996015667999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.322346892649993e-06,
"min": 9.322346892649993e-06,
"max": 0.0008439226686924498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10103578333333334,
"min": 0.10103578333333334,
"max": 0.1984332000000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30310735,
"min": 0.2072727,
"max": 0.58130755,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.168558833333331e-05,
"min": 6.168558833333331e-05,
"max": 0.00492181668,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001850567649999999,
"min": 0.0001850567649999999,
"max": 0.014067246745000001,
"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": "1750019630",
"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=Huggy --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750022051"
},
"total": 2420.151343394,
"count": 1,
"self": 0.44683660900000177,
"children": {
"run_training.setup": {
"total": 0.02225438400000712,
"count": 1,
"self": 0.02225438400000712
},
"TrainerController.start_learning": {
"total": 2419.682252401,
"count": 1,
"self": 3.9721389359870045,
"children": {
"TrainerController._reset_env": {
"total": 3.105331759000137,
"count": 1,
"self": 3.105331759000137
},
"TrainerController.advance": {
"total": 2412.484262008013,
"count": 231669,
"self": 4.294496111979697,
"children": {
"env_step": {
"total": 1916.3807671999634,
"count": 231669,
"self": 1519.0757724019147,
"children": {
"SubprocessEnvManager._take_step": {
"total": 394.7074315030575,
"count": 231669,
"self": 14.702570965110908,
"children": {
"TorchPolicy.evaluate": {
"total": 380.00486053794657,
"count": 222938,
"self": 380.00486053794657
}
}
},
"workers": {
"total": 2.5975632949912324,
"count": 231669,
"self": 0.0,
"children": {
"worker_root": {
"total": 2412.4797550839803,
"count": 231669,
"is_parallel": true,
"self": 1169.6689049659878,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008803410000837175,
"count": 1,
"is_parallel": true,
"self": 0.0002479990000665566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006323420000171609,
"count": 2,
"is_parallel": true,
"self": 0.0006323420000171609
}
}
},
"UnityEnvironment.step": {
"total": 0.029130324999869117,
"count": 1,
"is_parallel": true,
"self": 0.00031465999973079306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019384100005481741,
"count": 1,
"is_parallel": true,
"self": 0.00019384100005481741
},
"communicator.exchange": {
"total": 0.02791520000005221,
"count": 1,
"is_parallel": true,
"self": 0.02791520000005221
},
"steps_from_proto": {
"total": 0.0007066240000312973,
"count": 1,
"is_parallel": true,
"self": 0.00023475400007555436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047186999995574297,
"count": 2,
"is_parallel": true,
"self": 0.00047186999995574297
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1242.8108501179925,
"count": 231668,
"is_parallel": true,
"self": 37.11131610093071,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.24712639900645,
"count": 231668,
"is_parallel": true,
"self": 82.24712639900645
},
"communicator.exchange": {
"total": 1035.414194293027,
"count": 231668,
"is_parallel": true,
"self": 1035.414194293027
},
"steps_from_proto": {
"total": 88.03821332502821,
"count": 231668,
"is_parallel": true,
"self": 33.13994210012697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.89827122490124,
"count": 463336,
"is_parallel": true,
"self": 54.89827122490124
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.8089986960699,
"count": 231669,
"self": 6.227006990955488,
"children": {
"process_trajectory": {
"total": 148.20838335911412,
"count": 231669,
"self": 146.99220225811337,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2161811010007568,
"count": 10,
"self": 1.2161811010007568
}
}
},
"_update_policy": {
"total": 337.3736083460003,
"count": 97,
"self": 273.163416472009,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.21019187399133,
"count": 2910,
"self": 64.21019187399133
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.709998837730382e-07,
"count": 1,
"self": 8.709998837730382e-07
},
"TrainerController._save_models": {
"total": 0.120518827000069,
"count": 1,
"self": 0.0015900809999038756,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11892874600016512,
"count": 1,
"self": 0.11892874600016512
}
}
}
}
}
}
}