RL2 / run_logs /timers.json
Rubén Escobedo
Huggy
2660945
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4073175191879272,
"min": 1.4073066711425781,
"max": 1.429030179977417,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69990.125,
"min": 69242.9453125,
"max": 76442.5703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.40295358649789,
"min": 85.49826989619378,
"max": 442.3362831858407,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49487.0,
"min": 48951.0,
"max": 50071.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999913.0,
"min": 49569.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999913.0,
"min": 49569.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3709094524383545,
"min": 0.15921936929225922,
"max": 2.475139856338501,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1123.81103515625,
"min": 17.832569122314453,
"max": 1367.5396728515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.64041108182211,
"min": 2.0939514248498847,
"max": 3.936153358883328,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1725.55485278368,
"min": 234.5225595831871,
"max": 2172.5706474781036,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.64041108182211,
"min": 2.0939514248498847,
"max": 3.936153358883328,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1725.55485278368,
"min": 234.5225595831871,
"max": 2172.5706474781036,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018543461686446487,
"min": 0.013075986675191113,
"max": 0.021539940200293334,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.037086923372892974,
"min": 0.026151973350382225,
"max": 0.06461982060088,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.045039909146726134,
"min": 0.022054913515845934,
"max": 0.05981523038612472,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09007981829345227,
"min": 0.04410982703169187,
"max": 0.17944569115837417,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.460348513250009e-06,
"min": 4.460348513250009e-06,
"max": 0.00029533815155394997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.920697026500018e-06,
"min": 8.920697026500018e-06,
"max": 0.0008439712686762499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10148675000000001,
"min": 0.10148675000000001,
"max": 0.19844605000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20297350000000003,
"min": 0.20297350000000003,
"max": 0.58132375,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.418882500000017e-05,
"min": 8.418882500000017e-05,
"max": 0.004922457894999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016837765000000035,
"min": 0.00016837765000000035,
"max": 0.014068055125,
"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": "1677494132",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677496785"
},
"total": 2653.310034519,
"count": 1,
"self": 0.449371759999849,
"children": {
"run_training.setup": {
"total": 0.12231942099998605,
"count": 1,
"self": 0.12231942099998605
},
"TrainerController.start_learning": {
"total": 2652.738343338,
"count": 1,
"self": 4.556085328939389,
"children": {
"TrainerController._reset_env": {
"total": 11.654938730000026,
"count": 1,
"self": 11.654938730000026
},
"TrainerController.advance": {
"total": 2636.4083716780606,
"count": 231866,
"self": 5.104389377119787,
"children": {
"env_step": {
"total": 2050.365874197967,
"count": 231866,
"self": 1713.9001789780914,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.34031752794556,
"count": 231866,
"self": 17.44599352895682,
"children": {
"TorchPolicy.evaluate": {
"total": 315.89432399898874,
"count": 222940,
"self": 78.51459293598168,
"children": {
"TorchPolicy.sample_actions": {
"total": 237.37973106300706,
"count": 222940,
"self": 237.37973106300706
}
}
}
}
},
"workers": {
"total": 3.1253776919302254,
"count": 231866,
"self": 0.0,
"children": {
"worker_root": {
"total": 2643.3044093780013,
"count": 231866,
"is_parallel": true,
"self": 1250.5023924900102,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011806450000335644,
"count": 1,
"is_parallel": true,
"self": 0.00044125800002348115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007393870000100833,
"count": 2,
"is_parallel": true,
"self": 0.0007393870000100833
}
}
},
"UnityEnvironment.step": {
"total": 0.054600810000010824,
"count": 1,
"is_parallel": true,
"self": 0.00033274499992330675,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045000900001923583,
"count": 1,
"is_parallel": true,
"self": 0.00045000900001923583
},
"communicator.exchange": {
"total": 0.05107662099999288,
"count": 1,
"is_parallel": true,
"self": 0.05107662099999288
},
"steps_from_proto": {
"total": 0.0027414350000753984,
"count": 1,
"is_parallel": true,
"self": 0.00035597300006884325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002385462000006555,
"count": 2,
"is_parallel": true,
"self": 0.002385462000006555
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1392.8020168879912,
"count": 231865,
"is_parallel": true,
"self": 41.53090718605222,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.04243760789495,
"count": 231865,
"is_parallel": true,
"self": 90.04243760789495
},
"communicator.exchange": {
"total": 1161.1303928620073,
"count": 231865,
"is_parallel": true,
"self": 1161.1303928620073
},
"steps_from_proto": {
"total": 100.0982792320367,
"count": 231865,
"is_parallel": true,
"self": 42.953831114283844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.14444811775286,
"count": 463730,
"is_parallel": true,
"self": 57.14444811775286
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 580.9381081029738,
"count": 231866,
"self": 7.3998895331109225,
"children": {
"process_trajectory": {
"total": 179.74069458086433,
"count": 231866,
"self": 178.41491539086428,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3257791900000484,
"count": 10,
"self": 1.3257791900000484
}
}
},
"_update_policy": {
"total": 393.7975239889986,
"count": 96,
"self": 334.0239660150056,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.77355797399298,
"count": 2880,
"self": 59.77355797399298
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.349998097401112e-07,
"count": 1,
"self": 8.349998097401112e-07
},
"TrainerController._save_models": {
"total": 0.11894676600013554,
"count": 1,
"self": 0.002670455000043148,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11627631100009239,
"count": 1,
"self": 0.11627631100009239
}
}
}
}
}
}
}