ppo-Huggy / run_logs /timers.json
MindNetML's picture
Huggy
645b969
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403117060661316,
"min": 1.403117060661316,
"max": 1.425582766532898,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71206.7890625,
"min": 66913.9453125,
"max": 78699.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.18604651162791,
"min": 92.03738317757009,
"max": 402.784,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48807.0,
"min": 48807.0,
"max": 50348.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999952.0,
"min": 49982.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999952.0,
"min": 49982.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3590919971466064,
"min": 0.10294611752033234,
"max": 2.3981618881225586,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1115.8504638671875,
"min": 12.765318870544434,
"max": 1247.548583984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6301128616040654,
"min": 1.9221268214525715,
"max": 3.832234554747653,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1717.043383538723,
"min": 238.34372586011887,
"max": 1969.2576781511307,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6301128616040654,
"min": 1.9221268214525715,
"max": 3.832234554747653,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1717.043383538723,
"min": 238.34372586011887,
"max": 1969.2576781511307,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015974714481207127,
"min": 0.013327953298479163,
"max": 0.02031732095250239,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047924143443621385,
"min": 0.026655906596958327,
"max": 0.05605936483140492,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049644734255141675,
"min": 0.021611162616560854,
"max": 0.06189393196254969,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14893420276542502,
"min": 0.04322232523312171,
"max": 0.1668159995228052,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3737988754333468e-06,
"min": 3.3737988754333468e-06,
"max": 0.0002953635765454749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.012139662630004e-05,
"min": 1.012139662630004e-05,
"max": 0.0008443479185507002,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011245666666667,
"min": 0.1011245666666667,
"max": 0.198454525,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033737000000001,
"min": 0.20740165000000002,
"max": 0.5814493000000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.61158766666669e-05,
"min": 6.61158766666669e-05,
"max": 0.0049228807975,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001983476300000007,
"min": 0.0001983476300000007,
"max": 0.014074320070000002,
"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": "1687288297",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687290603"
},
"total": 2305.6844457139996,
"count": 1,
"self": 0.4388069659999019,
"children": {
"run_training.setup": {
"total": 0.04178251100000807,
"count": 1,
"self": 0.04178251100000807
},
"TrainerController.start_learning": {
"total": 2305.203856237,
"count": 1,
"self": 4.034312407975449,
"children": {
"TrainerController._reset_env": {
"total": 4.162646659000018,
"count": 1,
"self": 4.162646659000018
},
"TrainerController.advance": {
"total": 2296.8789820420243,
"count": 231469,
"self": 4.155643312038137,
"children": {
"env_step": {
"total": 1792.6375126000105,
"count": 231469,
"self": 1506.4410596479524,
"children": {
"SubprocessEnvManager._take_step": {
"total": 283.56110490098945,
"count": 231469,
"self": 16.61370349092556,
"children": {
"TorchPolicy.evaluate": {
"total": 266.9474014100639,
"count": 223098,
"self": 266.9474014100639
}
}
},
"workers": {
"total": 2.6353480510684903,
"count": 231469,
"self": 0.0,
"children": {
"worker_root": {
"total": 2297.674205831052,
"count": 231469,
"is_parallel": true,
"self": 1065.5054615140257,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009017269999844757,
"count": 1,
"is_parallel": true,
"self": 0.00026374899999837,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006379779999861057,
"count": 2,
"is_parallel": true,
"self": 0.0006379779999861057
}
}
},
"UnityEnvironment.step": {
"total": 0.028853071000014552,
"count": 1,
"is_parallel": true,
"self": 0.0003575850000174796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021213799999486582,
"count": 1,
"is_parallel": true,
"self": 0.00021213799999486582
},
"communicator.exchange": {
"total": 0.027472329000033824,
"count": 1,
"is_parallel": true,
"self": 0.027472329000033824
},
"steps_from_proto": {
"total": 0.0008110189999683826,
"count": 1,
"is_parallel": true,
"self": 0.00021464499997136954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000596373999997013,
"count": 2,
"is_parallel": true,
"self": 0.000596373999997013
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1232.1687443170263,
"count": 231468,
"is_parallel": true,
"self": 38.508316107092696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.93252758893931,
"count": 231468,
"is_parallel": true,
"self": 76.93252758893931
},
"communicator.exchange": {
"total": 1025.0955088759702,
"count": 231468,
"is_parallel": true,
"self": 1025.0955088759702
},
"steps_from_proto": {
"total": 91.63239174502411,
"count": 231468,
"is_parallel": true,
"self": 32.52218739096605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.110204354058055,
"count": 462936,
"is_parallel": true,
"self": 59.110204354058055
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 500.0858261299758,
"count": 231469,
"self": 6.1692345590550985,
"children": {
"process_trajectory": {
"total": 126.97182945092078,
"count": 231469,
"self": 125.68531085192075,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2865185990000327,
"count": 10,
"self": 1.2865185990000327
}
}
},
"_update_policy": {
"total": 366.94476211999995,
"count": 97,
"self": 308.2891726150059,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.655589504994055,
"count": 2910,
"self": 58.655589504994055
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7501999991509365e-05,
"count": 1,
"self": 1.7501999991509365e-05
},
"TrainerController._save_models": {
"total": 0.12789762600004906,
"count": 1,
"self": 0.001967452999906527,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12593017300014253,
"count": 1,
"self": 0.12593017300014253
}
}
}
}
}
}
}