ppo-Huggy / run_logs /timers.json
shermansiu's picture
Huggy
4756dc4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045941829681396,
"min": 1.4045941829681396,
"max": 1.4280754327774048,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70014.8046875,
"min": 69153.828125,
"max": 77040.1796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.17676767676768,
"min": 82.38513513513513,
"max": 389.06201550387595,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49407.0,
"min": 48772.0,
"max": 50189.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999970.0,
"min": 49940.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999970.0,
"min": 49940.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.425067663192749,
"min": 0.09718458354473114,
"max": 2.448483467102051,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1440.490234375,
"min": 12.439626693725586,
"max": 1457.9351806640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.870018548636324,
"min": 1.6564193745143712,
"max": 3.911249404169541,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2298.7910178899765,
"min": 212.0216799378395,
"max": 2298.7910178899765,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.870018548636324,
"min": 1.6564193745143712,
"max": 3.911249404169541,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2298.7910178899765,
"min": 212.0216799378395,
"max": 2298.7910178899765,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01638779169356389,
"min": 0.012883907392415494,
"max": 0.019538051799301886,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04916337508069167,
"min": 0.02576781478483099,
"max": 0.058614155397905654,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059377102926373486,
"min": 0.021487734963496527,
"max": 0.06514945858054692,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17813130877912045,
"min": 0.042975469926993054,
"max": 0.19544837574164076,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3204488932166607e-06,
"min": 3.3204488932166607e-06,
"max": 0.00029533507655497496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.961346679649982e-06,
"min": 9.961346679649982e-06,
"max": 0.0008440345686551499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110678333333335,
"min": 0.10110678333333335,
"max": 0.198445025,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30332035000000007,
"min": 0.2073766,
"max": 0.5813448499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.522848833333325e-05,
"min": 6.522848833333325e-05,
"max": 0.0049224067475,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019568546499999974,
"min": 0.00019568546499999974,
"max": 0.014069108015000002,
"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": "1679788711",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679791060"
},
"total": 2348.864770883,
"count": 1,
"self": 0.43416602899969803,
"children": {
"run_training.setup": {
"total": 0.10839390600000343,
"count": 1,
"self": 0.10839390600000343
},
"TrainerController.start_learning": {
"total": 2348.3222109480002,
"count": 1,
"self": 4.125977459022124,
"children": {
"TrainerController._reset_env": {
"total": 9.222934737999992,
"count": 1,
"self": 9.222934737999992
},
"TrainerController.advance": {
"total": 2334.8593375549785,
"count": 232101,
"self": 4.615062034042694,
"children": {
"env_step": {
"total": 1823.7319997849306,
"count": 232101,
"self": 1540.4988746459253,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.44604845399436,
"count": 232101,
"self": 16.490261090029037,
"children": {
"TorchPolicy.evaluate": {
"total": 263.9557873639653,
"count": 222886,
"self": 263.9557873639653
}
}
},
"workers": {
"total": 2.787076685011101,
"count": 232101,
"self": 0.0,
"children": {
"worker_root": {
"total": 2340.4956469199615,
"count": 232101,
"is_parallel": true,
"self": 1088.7306008899764,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011268289999861736,
"count": 1,
"is_parallel": true,
"self": 0.0002992449999794644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008275840000067092,
"count": 2,
"is_parallel": true,
"self": 0.0008275840000067092
}
}
},
"UnityEnvironment.step": {
"total": 0.04059011300000748,
"count": 1,
"is_parallel": true,
"self": 0.0003040969999972276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002024899999923946,
"count": 1,
"is_parallel": true,
"self": 0.0002024899999923946
},
"communicator.exchange": {
"total": 0.03943853100000183,
"count": 1,
"is_parallel": true,
"self": 0.03943853100000183
},
"steps_from_proto": {
"total": 0.0006449950000160243,
"count": 1,
"is_parallel": true,
"self": 0.00018455000002859379,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004604449999874305,
"count": 2,
"is_parallel": true,
"self": 0.0004604449999874305
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1251.7650460299851,
"count": 232100,
"is_parallel": true,
"self": 38.51336195484373,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.66817580997866,
"count": 232100,
"is_parallel": true,
"self": 76.66817580997866
},
"communicator.exchange": {
"total": 1048.37200651509,
"count": 232100,
"is_parallel": true,
"self": 1048.37200651509
},
"steps_from_proto": {
"total": 88.21150175007244,
"count": 232100,
"is_parallel": true,
"self": 33.417469221095985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.79403252897646,
"count": 464200,
"is_parallel": true,
"self": 54.79403252897646
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 506.51227573600505,
"count": 232101,
"self": 6.5187732580002375,
"children": {
"process_trajectory": {
"total": 141.19951162700585,
"count": 232101,
"self": 139.78588300100614,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4136286259997064,
"count": 10,
"self": 1.4136286259997064
}
}
},
"_update_policy": {
"total": 358.79399085099897,
"count": 97,
"self": 300.72900573700065,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.06498511399832,
"count": 2910,
"self": 58.06498511399832
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.739998520468362e-07,
"count": 1,
"self": 8.739998520468362e-07
},
"TrainerController._save_models": {
"total": 0.11396032199991168,
"count": 1,
"self": 0.002060727999833034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11189959400007865,
"count": 1,
"self": 0.11189959400007865
}
}
}
}
}
}
}