ppo-Huggy / run_logs /timers.json
preslaff's picture
Initial Huggy commit
62b48f3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054542779922485,
"min": 1.4054542779922485,
"max": 1.4292277097702026,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69326.84375,
"min": 68744.859375,
"max": 76322.3046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.9718045112782,
"min": 83.92869269949067,
"max": 422.97478991596637,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49461.0,
"min": 48901.0,
"max": 50334.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49774.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49774.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3829057216644287,
"min": 0.1211981549859047,
"max": 2.4492650032043457,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1267.705810546875,
"min": 14.301382064819336,
"max": 1435.206298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6764475089266786,
"min": 1.7918531419867176,
"max": 3.9405214584098673,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1955.870074748993,
"min": 211.43867075443268,
"max": 2267.908268094063,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6764475089266786,
"min": 1.7918531419867176,
"max": 3.9405214584098673,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1955.870074748993,
"min": 211.43867075443268,
"max": 2267.908268094063,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014744528976087976,
"min": 0.013564466007755982,
"max": 0.0210475033178227,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04423358692826393,
"min": 0.027128932015511965,
"max": 0.05521997262452108,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05648226274384393,
"min": 0.02114696645488342,
"max": 0.05967976022511721,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16944678823153178,
"min": 0.04229393290976684,
"max": 0.16944678823153178,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.085148971650012e-06,
"min": 3.085148971650012e-06,
"max": 0.00029531175156274995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.255446914950036e-06,
"min": 9.255446914950036e-06,
"max": 0.0008438973187008998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10102835,
"min": 0.10102835,
"max": 0.19843725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30308505,
"min": 0.20718925000000007,
"max": 0.5812991000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.131466500000018e-05,
"min": 6.131466500000018e-05,
"max": 0.004922018775000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018394399500000052,
"min": 0.00018394399500000052,
"max": 0.014066825090000002,
"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": "1739359050",
"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",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739361432"
},
"total": 2382.130310857,
"count": 1,
"self": 0.4382459380003638,
"children": {
"run_training.setup": {
"total": 0.022861959000010756,
"count": 1,
"self": 0.022861959000010756
},
"TrainerController.start_learning": {
"total": 2381.66920296,
"count": 1,
"self": 4.246979382962309,
"children": {
"TrainerController._reset_env": {
"total": 3.0990785529997993,
"count": 1,
"self": 3.0990785529997993
},
"TrainerController.advance": {
"total": 2374.211116433038,
"count": 231760,
"self": 4.463505677160356,
"children": {
"env_step": {
"total": 1897.3016714299245,
"count": 231760,
"self": 1484.4501400798213,
"children": {
"SubprocessEnvManager._take_step": {
"total": 410.20904988509255,
"count": 231760,
"self": 15.624841858319542,
"children": {
"TorchPolicy.evaluate": {
"total": 394.584208026773,
"count": 222920,
"self": 394.584208026773
}
}
},
"workers": {
"total": 2.6424814650106327,
"count": 231760,
"self": 0.0,
"children": {
"worker_root": {
"total": 2374.5249632329683,
"count": 231760,
"is_parallel": true,
"self": 1168.4588263709097,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010140449999198609,
"count": 1,
"is_parallel": true,
"self": 0.00036149700008536456,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006525479998344963,
"count": 2,
"is_parallel": true,
"self": 0.0006525479998344963
}
}
},
"UnityEnvironment.step": {
"total": 0.028966463999950065,
"count": 1,
"is_parallel": true,
"self": 0.0003055439999570808,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018777700006467057,
"count": 1,
"is_parallel": true,
"self": 0.00018777700006467057
},
"communicator.exchange": {
"total": 0.027774402999966696,
"count": 1,
"is_parallel": true,
"self": 0.027774402999966696
},
"steps_from_proto": {
"total": 0.0006987399999616173,
"count": 1,
"is_parallel": true,
"self": 0.00017943600005310145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005193039999085158,
"count": 2,
"is_parallel": true,
"self": 0.0005193039999085158
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1206.0661368620586,
"count": 231759,
"is_parallel": true,
"self": 36.876499365089785,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.42707286405607,
"count": 231759,
"is_parallel": true,
"self": 78.42707286405607
},
"communicator.exchange": {
"total": 1005.483359027988,
"count": 231759,
"is_parallel": true,
"self": 1005.483359027988
},
"steps_from_proto": {
"total": 85.27920560492475,
"count": 231759,
"is_parallel": true,
"self": 29.765758591742724,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.51344701318203,
"count": 463518,
"is_parallel": true,
"self": 55.51344701318203
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.4459393259533,
"count": 231760,
"self": 6.24201064094018,
"children": {
"process_trajectory": {
"total": 155.04763075401456,
"count": 231760,
"self": 153.72778334601412,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3198474080004416,
"count": 10,
"self": 1.3198474080004416
}
}
},
"_update_policy": {
"total": 311.15629793099856,
"count": 97,
"self": 247.20523207001543,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.951065860983135,
"count": 2910,
"self": 63.951065860983135
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.699998943484388e-07,
"count": 1,
"self": 8.699998943484388e-07
},
"TrainerController._save_models": {
"total": 0.11202772099977665,
"count": 1,
"self": 0.0018992349996551638,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11012848600012148,
"count": 1,
"self": 0.11012848600012148
}
}
}
}
}
}
}