ppo-Huggy / run_logs /timers.json
jamesup's picture
Huggy trained
3099df5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4000617265701294,
"min": 1.4000617265701294,
"max": 1.4296114444732666,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68603.0234375,
"min": 68603.0234375,
"max": 76903.2109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.14285714285714,
"min": 89.52844036697248,
"max": 409.94262295081967,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49560.0,
"min": 48793.0,
"max": 50340.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49856.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49856.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.347660779953003,
"min": 0.05545629560947418,
"max": 2.4096662998199463,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1150.353759765625,
"min": 6.710211753845215,
"max": 1303.529052734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5857214812113316,
"min": 1.5958672021785059,
"max": 3.883461022350986,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1757.0035257935524,
"min": 193.0999314635992,
"max": 2030.8787176012993,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5857214812113316,
"min": 1.5958672021785059,
"max": 3.883461022350986,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1757.0035257935524,
"min": 193.0999314635992,
"max": 2030.8787176012993,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0169097591805136,
"min": 0.012707807274030833,
"max": 0.019295883309031422,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0338195183610272,
"min": 0.025415614548061665,
"max": 0.05788764992709426,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04514318990210692,
"min": 0.022766839185108738,
"max": 0.06276925920198362,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09028637980421383,
"min": 0.045533678370217476,
"max": 0.18624878873427708,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.548023484024991e-06,
"min": 4.548023484024991e-06,
"max": 0.00029531175156274995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.096046968049983e-06,
"min": 9.096046968049983e-06,
"max": 0.00084400816866395,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10151597500000001,
"min": 0.10151597500000001,
"max": 0.19843725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20303195000000002,
"min": 0.20303195000000002,
"max": 0.58133605,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.564715249999985e-05,
"min": 8.564715249999985e-05,
"max": 0.004922018774999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001712943049999997,
"min": 0.0001712943049999997,
"max": 0.014068668895,
"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": "1672827390",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/home/jamesup/Documents/source/deep-rl-class/env/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.13.1+cu116",
"numpy_version": "1.23.3",
"end_time_seconds": "1672829314"
},
"total": 1924.4575360198505,
"count": 1,
"self": 0.3200341719202697,
"children": {
"run_training.setup": {
"total": 0.03551440592855215,
"count": 1,
"self": 0.03551440592855215
},
"TrainerController.start_learning": {
"total": 1924.1019874420017,
"count": 1,
"self": 2.49790434865281,
"children": {
"TrainerController._reset_env": {
"total": 1.650242525152862,
"count": 1,
"self": 1.650242525152862
},
"TrainerController.advance": {
"total": 1919.8805857170373,
"count": 231828,
"self": 2.548338268417865,
"children": {
"env_step": {
"total": 1577.554365600925,
"count": 231828,
"self": 1401.5958394627087,
"children": {
"SubprocessEnvManager._take_step": {
"total": 174.33632413158193,
"count": 231828,
"self": 8.874491612892598,
"children": {
"TorchPolicy.evaluate": {
"total": 165.46183251868933,
"count": 222926,
"self": 41.691447546705604,
"children": {
"TorchPolicy.sample_actions": {
"total": 123.77038497198373,
"count": 222926,
"self": 123.77038497198373
}
}
}
}
},
"workers": {
"total": 1.6222020066343248,
"count": 231828,
"self": 0.0,
"children": {
"worker_root": {
"total": 1916.4834956126288,
"count": 231828,
"is_parallel": true,
"self": 717.4080909281038,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011593913659453392,
"count": 1,
"is_parallel": true,
"self": 0.0005444749258458614,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006149164400994778,
"count": 2,
"is_parallel": true,
"self": 0.0006149164400994778
}
}
},
"UnityEnvironment.step": {
"total": 0.02378166513517499,
"count": 1,
"is_parallel": true,
"self": 0.0003095516003668308,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022613583132624626,
"count": 1,
"is_parallel": true,
"self": 0.00022613583132624626
},
"communicator.exchange": {
"total": 0.02249954780563712,
"count": 1,
"is_parallel": true,
"self": 0.02249954780563712
},
"steps_from_proto": {
"total": 0.0007464298978447914,
"count": 1,
"is_parallel": true,
"self": 0.00021879607811570168,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005276338197290897,
"count": 2,
"is_parallel": true,
"self": 0.0005276338197290897
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1199.075404684525,
"count": 231827,
"is_parallel": true,
"self": 41.29875669023022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.55164432013407,
"count": 231827,
"is_parallel": true,
"self": 90.55164432013407
},
"communicator.exchange": {
"total": 977.533335887827,
"count": 231827,
"is_parallel": true,
"self": 977.533335887827
},
"steps_from_proto": {
"total": 89.69166778633371,
"count": 231827,
"is_parallel": true,
"self": 33.01262605097145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.67904173536226,
"count": 463654,
"is_parallel": true,
"self": 56.67904173536226
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 339.7778818476945,
"count": 231828,
"self": 3.5157480407506227,
"children": {
"process_trajectory": {
"total": 110.99438810162246,
"count": 231828,
"self": 110.27636627666652,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7180218249559402,
"count": 10,
"self": 0.7180218249559402
}
}
},
"_update_policy": {
"total": 225.26774570532143,
"count": 96,
"self": 180.0595419863239,
"children": {
"TorchPPOOptimizer.update": {
"total": 45.20820371899754,
"count": 2880,
"self": 45.20820371899754
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.501803338527679e-07,
"count": 1,
"self": 7.501803338527679e-07
},
"TrainerController._save_models": {
"total": 0.07325410097837448,
"count": 1,
"self": 0.0015057711862027645,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07174832979217172,
"count": 1,
"self": 0.07174832979217172
}
}
}
}
}
}
}