ppo-Huggy / run_logs /timers.json
SmartPy's picture
Huggy
73fbe1c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.2994767427444458,
"min": 1.2994767427444458,
"max": 1.4202715158462524,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 64791.91015625,
"min": 62157.8515625,
"max": 78374.84375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 738.8656716417911,
"min": 436.81739130434784,
"max": 749.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49504.0,
"min": 49278.0,
"max": 50542.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999520.0,
"min": 49600.0,
"max": 1999520.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999520.0,
"min": 49600.0,
"max": 1999520.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.00045388098806142807,
"min": -0.01361062191426754,
"max": 0.024214955046772957,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.030410025268793106,
"min": -0.91191166639328,
"max": 2.760504961013794,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": -0.02151003446596772,
"min": -3.6768716662677368,
"max": 1.5218163911057145,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": -1.4411723092198372,
"min": -246.35040163993835,
"max": 173.48706858605146,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": -0.02151003446596772,
"min": -3.6768716662677368,
"max": 1.5218163911057145,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": -1.4411723092198372,
"min": -246.35040163993835,
"max": 173.48706858605146,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015243637195521843,
"min": 0.01467561419658523,
"max": 0.019269247038027973,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.030487274391043685,
"min": 0.02935122839317046,
"max": 0.05741662231357623,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0001271978856948408,
"min": 6.225213749833833e-05,
"max": 0.005055132885172498,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0002543957713896816,
"min": 0.00014687132606923116,
"max": 0.010110265770344996,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.931673689475004e-06,
"min": 3.931673689475004e-06,
"max": 0.00029533245155584993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.863347378950008e-06,
"min": 7.863347378950008e-06,
"max": 0.0008441631186123,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131052500000001,
"min": 0.10131052500000001,
"max": 0.19844415,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20262105000000002,
"min": 0.20262105000000002,
"max": 0.5813877000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.539519750000007e-05,
"min": 7.539519750000007e-05,
"max": 0.004922363085,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015079039500000014,
"min": 0.00015079039500000014,
"max": 0.01407124623,
"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": "1670578565",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --resume",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1670580966"
},
"total": 2401.1629619299997,
"count": 1,
"self": 0.380932066999776,
"children": {
"run_training.setup": {
"total": 0.10646700000006604,
"count": 1,
"self": 0.10646700000006604
},
"TrainerController.start_learning": {
"total": 2400.675562863,
"count": 1,
"self": 3.9738216540354188,
"children": {
"TrainerController._reset_env": {
"total": 6.129866509999829,
"count": 1,
"self": 6.129866509999829
},
"TrainerController.advance": {
"total": 2390.407823918965,
"count": 224285,
"self": 4.009598841847037,
"children": {
"env_step": {
"total": 1842.0509280340416,
"count": 224285,
"self": 1535.4346537462288,
"children": {
"SubprocessEnvManager._take_step": {
"total": 303.93122397602156,
"count": 224285,
"self": 15.016771797183083,
"children": {
"TorchPolicy.evaluate": {
"total": 288.9144521788385,
"count": 222875,
"self": 69.34641265780738,
"children": {
"TorchPolicy.sample_actions": {
"total": 219.5680395210311,
"count": 222875,
"self": 219.5680395210311
}
}
}
}
},
"workers": {
"total": 2.6850503117912012,
"count": 224285,
"self": 0.0,
"children": {
"worker_root": {
"total": 2392.608024884129,
"count": 224285,
"is_parallel": true,
"self": 1130.2781380330955,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008936510000694398,
"count": 1,
"is_parallel": true,
"self": 0.00036040300005879544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005332480000106443,
"count": 2,
"is_parallel": true,
"self": 0.0005332480000106443
}
}
},
"UnityEnvironment.step": {
"total": 0.029431801000100677,
"count": 1,
"is_parallel": true,
"self": 0.00026103700020030374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002068679998501466,
"count": 1,
"is_parallel": true,
"self": 0.0002068679998501466
},
"communicator.exchange": {
"total": 0.028012364999995043,
"count": 1,
"is_parallel": true,
"self": 0.028012364999995043
},
"steps_from_proto": {
"total": 0.0009515310000551835,
"count": 1,
"is_parallel": true,
"self": 0.00026851799998439674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006830130000707868,
"count": 2,
"is_parallel": true,
"self": 0.0006830130000707868
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1262.3298868510335,
"count": 224284,
"is_parallel": true,
"self": 34.07347406495569,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.92048868194138,
"count": 224284,
"is_parallel": true,
"self": 80.92048868194138
},
"communicator.exchange": {
"total": 1053.1908401971457,
"count": 224284,
"is_parallel": true,
"self": 1053.1908401971457
},
"steps_from_proto": {
"total": 94.14508390699075,
"count": 224284,
"is_parallel": true,
"self": 40.643456255949104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.501627651041645,
"count": 448568,
"is_parallel": true,
"self": 53.501627651041645
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 544.3472970430762,
"count": 224285,
"self": 6.533634771242305,
"children": {
"process_trajectory": {
"total": 114.21470234783578,
"count": 224285,
"self": 113.57111285283622,
"children": {
"RLTrainer._checkpoint": {
"total": 0.64358949499956,
"count": 4,
"self": 0.64358949499956
}
}
},
"_update_policy": {
"total": 423.5989599239981,
"count": 95,
"self": 342.73976052197327,
"children": {
"TorchPPOOptimizer.update": {
"total": 80.85919940202484,
"count": 3800,
"self": 80.85919940202484
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0799999472510535e-06,
"count": 1,
"self": 1.0799999472510535e-06
},
"TrainerController._save_models": {
"total": 0.16404969999985042,
"count": 1,
"self": 0.0037027049997959693,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16034699500005445,
"count": 1,
"self": 0.16034699500005445
}
}
}
}
}
}
}