ppo-Huggy / run_logs /timers.json
Hideki Ishiguro
Huggy
3debebe
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045759439468384,
"min": 1.4045759439468384,
"max": 1.431074619293213,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69513.8671875,
"min": 68345.6171875,
"max": 78016.59375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.49598393574297,
"min": 96.64554455445544,
"max": 388.2230769230769,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49549.0,
"min": 48806.0,
"max": 50469.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999948.0,
"min": 49850.0,
"max": 1999948.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999948.0,
"min": 49850.0,
"max": 1999948.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.333069324493408,
"min": 0.12892621755599976,
"max": 2.357923984527588,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1161.8685302734375,
"min": 16.631481170654297,
"max": 1184.196533203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.64190338833265,
"min": 1.8001783767411874,
"max": 3.7910542996536716,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1813.6678873896599,
"min": 232.2230105996132,
"max": 1875.592817246914,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.64190338833265,
"min": 1.8001783767411874,
"max": 3.7910542996536716,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1813.6678873896599,
"min": 232.2230105996132,
"max": 1875.592817246914,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018117416448593656,
"min": 0.012866589489729246,
"max": 0.021807959090559353,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05435224934578097,
"min": 0.02937085572242116,
"max": 0.05818379348559878,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053578612829248105,
"min": 0.019164031278342007,
"max": 0.06246580978234609,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1607358384877443,
"min": 0.038328062556684014,
"max": 0.1790295881529649,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.110048963350007e-06,
"min": 3.110048963350007e-06,
"max": 0.000295353376548875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.33014689005002e-06,
"min": 9.33014689005002e-06,
"max": 0.0008442685685771498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10103665,
"min": 0.10103665,
"max": 0.19845112500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30310995,
"min": 0.20721079999999997,
"max": 0.5814228499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.172883500000011e-05,
"min": 6.172883500000011e-05,
"max": 0.004922711137500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018518650500000034,
"min": 0.00018518650500000034,
"max": 0.014073000215,
"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": "1685670492",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685672770"
},
"total": 2278.914928595,
"count": 1,
"self": 0.43863638499988156,
"children": {
"run_training.setup": {
"total": 0.061687674000012294,
"count": 1,
"self": 0.061687674000012294
},
"TrainerController.start_learning": {
"total": 2278.4146045360003,
"count": 1,
"self": 4.002055575988834,
"children": {
"TrainerController._reset_env": {
"total": 4.445645661999976,
"count": 1,
"self": 4.445645661999976
},
"TrainerController.advance": {
"total": 2269.848890467011,
"count": 231089,
"self": 4.149573418033924,
"children": {
"env_step": {
"total": 1763.718900414016,
"count": 231089,
"self": 1485.2372458760697,
"children": {
"SubprocessEnvManager._take_step": {
"total": 275.8275463809847,
"count": 231089,
"self": 15.83440333901143,
"children": {
"TorchPolicy.evaluate": {
"total": 259.99314304197327,
"count": 222884,
"self": 259.99314304197327
}
}
},
"workers": {
"total": 2.654108156961513,
"count": 231089,
"self": 0.0,
"children": {
"worker_root": {
"total": 2271.412296367025,
"count": 231089,
"is_parallel": true,
"self": 1053.960557016951,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011022669999931622,
"count": 1,
"is_parallel": true,
"self": 0.0003217860000006567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007804809999925055,
"count": 2,
"is_parallel": true,
"self": 0.0007804809999925055
}
}
},
"UnityEnvironment.step": {
"total": 0.030275692000003573,
"count": 1,
"is_parallel": true,
"self": 0.0003510319999975309,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022537799998190167,
"count": 1,
"is_parallel": true,
"self": 0.00022537799998190167
},
"communicator.exchange": {
"total": 0.02897666200001936,
"count": 1,
"is_parallel": true,
"self": 0.02897666200001936
},
"steps_from_proto": {
"total": 0.0007226200000047811,
"count": 1,
"is_parallel": true,
"self": 0.00020007200004101833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005225479999637628,
"count": 2,
"is_parallel": true,
"self": 0.0005225479999637628
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1217.4517393500741,
"count": 231088,
"is_parallel": true,
"self": 38.42408177406037,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.07098994099323,
"count": 231088,
"is_parallel": true,
"self": 77.07098994099323
},
"communicator.exchange": {
"total": 1009.7944374780028,
"count": 231088,
"is_parallel": true,
"self": 1009.7944374780028
},
"steps_from_proto": {
"total": 92.16223015701775,
"count": 231088,
"is_parallel": true,
"self": 33.06836848096049,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.09386167605726,
"count": 462176,
"is_parallel": true,
"self": 59.09386167605726
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.9804166349614,
"count": 231089,
"self": 6.392880661978381,
"children": {
"process_trajectory": {
"total": 123.77172620698195,
"count": 231089,
"self": 122.43936547898164,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3323607280003102,
"count": 10,
"self": 1.3323607280003102
}
}
},
"_update_policy": {
"total": 371.81580976600105,
"count": 97,
"self": 312.8197422819987,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.99606748400237,
"count": 2910,
"self": 58.99606748400237
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0700000530050602e-06,
"count": 1,
"self": 1.0700000530050602e-06
},
"TrainerController._save_models": {
"total": 0.11801176100016164,
"count": 1,
"self": 0.0020023329998366535,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11600942800032499,
"count": 1,
"self": 0.11600942800032499
}
}
}
}
}
}
}