ppo-Huggy / run_logs /timers.json
AdamShih's picture
Huggy
0e5b48e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4093321561813354,
"min": 1.4093321561813354,
"max": 1.4284718036651611,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69702.75,
"min": 69472.828125,
"max": 77139.3828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.48069498069498,
"min": 84.21124361158432,
"max": 405.508064516129,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49459.0,
"min": 49301.0,
"max": 50283.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999908.0,
"min": 49674.0,
"max": 1999908.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999908.0,
"min": 49674.0,
"max": 1999908.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3397269248962402,
"min": 0.09147118777036667,
"max": 2.459613800048828,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1211.978515625,
"min": 11.250956535339355,
"max": 1355.316162109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6078178334880517,
"min": 1.9502360245318917,
"max": 3.9170321260288263,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1868.849637746811,
"min": 239.87903101742268,
"max": 2122.901255786419,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6078178334880517,
"min": 1.9502360245318917,
"max": 3.9170321260288263,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1868.849637746811,
"min": 239.87903101742268,
"max": 2122.901255786419,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015784238837818522,
"min": 0.013622187764849514,
"max": 0.019733427871445504,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.031568477675637044,
"min": 0.02724437552969903,
"max": 0.05404670268580958,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051529312133789064,
"min": 0.019857661162192623,
"max": 0.058469501510262485,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10305862426757813,
"min": 0.039715322324385245,
"max": 0.17540850453078746,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.634273455275007e-06,
"min": 4.634273455275007e-06,
"max": 0.000295344526551825,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.268546910550014e-06,
"min": 9.268546910550014e-06,
"max": 0.0008439462186846,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10154472499999999,
"min": 0.10154472499999999,
"max": 0.19844817499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20308944999999998,
"min": 0.20308944999999998,
"max": 0.5813154,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.708177750000012e-05,
"min": 8.708177750000012e-05,
"max": 0.0049225639325,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017416355500000024,
"min": 0.00017416355500000024,
"max": 0.014067638459999997,
"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": "1745564042",
"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 --torch-device=cuda:0",
"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": "1745566502"
},
"total": 2459.325533802,
"count": 1,
"self": 0.764520063999953,
"children": {
"run_training.setup": {
"total": 0.02829446900000221,
"count": 1,
"self": 0.02829446900000221
},
"TrainerController.start_learning": {
"total": 2458.532719269,
"count": 1,
"self": 4.500587068098866,
"children": {
"TrainerController._reset_env": {
"total": 3.2579223979998915,
"count": 1,
"self": 3.2579223979998915
},
"TrainerController.advance": {
"total": 2450.6257153469014,
"count": 231898,
"self": 4.544180157820392,
"children": {
"env_step": {
"total": 1969.2805404559786,
"count": 231898,
"self": 1551.6961478788953,
"children": {
"SubprocessEnvManager._take_step": {
"total": 414.87285856297194,
"count": 231898,
"self": 15.872578991973796,
"children": {
"TorchPolicy.evaluate": {
"total": 399.00027957099815,
"count": 222964,
"self": 399.00027957099815
}
}
},
"workers": {
"total": 2.711534014111294,
"count": 231898,
"self": 0.0,
"children": {
"worker_root": {
"total": 2450.863884171945,
"count": 231898,
"is_parallel": true,
"self": 1185.476526554985,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009001779999380233,
"count": 1,
"is_parallel": true,
"self": 0.00027383199994801544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006263459999900078,
"count": 2,
"is_parallel": true,
"self": 0.0006263459999900078
}
}
},
"UnityEnvironment.step": {
"total": 0.03043878800008315,
"count": 1,
"is_parallel": true,
"self": 0.0002817189999859693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002037880000216319,
"count": 1,
"is_parallel": true,
"self": 0.0002037880000216319
},
"communicator.exchange": {
"total": 0.029114477000007355,
"count": 1,
"is_parallel": true,
"self": 0.029114477000007355
},
"steps_from_proto": {
"total": 0.000838804000068194,
"count": 1,
"is_parallel": true,
"self": 0.00022428700003729318,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006145170000309008,
"count": 2,
"is_parallel": true,
"self": 0.0006145170000309008
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1265.38735761696,
"count": 231897,
"is_parallel": true,
"self": 36.70204336778261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.97567276308735,
"count": 231897,
"is_parallel": true,
"self": 82.97567276308735
},
"communicator.exchange": {
"total": 1057.583565210077,
"count": 231897,
"is_parallel": true,
"self": 1057.583565210077
},
"steps_from_proto": {
"total": 88.1260762760129,
"count": 231897,
"is_parallel": true,
"self": 32.64664348794315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.479432788069744,
"count": 463794,
"is_parallel": true,
"self": 55.479432788069744
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 476.80099473310236,
"count": 231898,
"self": 6.580934956049987,
"children": {
"process_trajectory": {
"total": 160.9868819440511,
"count": 231898,
"self": 159.5603874150512,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4264945289999105,
"count": 10,
"self": 1.4264945289999105
}
}
},
"_update_policy": {
"total": 309.23317783300126,
"count": 96,
"self": 247.13605453200455,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.097123300996714,
"count": 2880,
"self": 62.097123300996714
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3869998838345055e-06,
"count": 1,
"self": 1.3869998838345055e-06
},
"TrainerController._save_models": {
"total": 0.14849306899986914,
"count": 1,
"self": 0.002483228000073723,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14600984099979541,
"count": 1,
"self": 0.14600984099979541
}
}
}
}
}
}
}