dasaprakashk's picture
First Push
ea7a7fa
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.44048386812210083,
"min": 0.43022671341896057,
"max": 2.851201295852661,
"count": 200
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 4520.68603515625,
"min": 4107.8046875,
"max": 29261.87890625,
"count": 200
},
"SnowballTarget.Step.mean": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Step.sum": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.347075462341309,
"min": 0.4112275242805481,
"max": 14.531590461730957,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2941.150390625,
"min": 79.77813720703125,
"max": 2978.97607421875,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0677945499022505,
"min": 0.06201875470052233,
"max": 0.07796704177313836,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3389727495112525,
"min": 0.24807501880208932,
"max": 0.38828099012037043,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.146025655754641,
"min": 0.1125481730400055,
"max": 0.2838909823520511,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.730128278773205,
"min": 0.450192692160022,
"max": 1.4194549117602555,
"count": 200
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032997656000039e-07,
"min": 7.032997656000039e-07,
"max": 0.00029918820027059994,
"count": 200
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5164988280000196e-06,
"min": 3.5164988280000196e-06,
"max": 0.0014885160038279998,
"count": 200
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10023440000000002,
"min": 0.10023440000000002,
"max": 0.1997294,
"count": 200
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5011720000000001,
"min": 0.4029176,
"max": 0.996172,
"count": 200
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.1696560000000067e-05,
"min": 2.1696560000000067e-05,
"max": 0.004986497059999999,
"count": 200
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00010848280000000034,
"min": 0.00010848280000000034,
"max": 0.024808982800000004,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.2,
"min": 3.4545454545454546,
"max": 28.818181818181817,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1551.0,
"min": 152.0,
"max": 1584.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.2,
"min": 3.4545454545454546,
"max": 28.818181818181817,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1551.0,
"min": 152.0,
"max": 1584.0,
"count": 200
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679166253",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1679171009"
},
"total": 4756.353230739,
"count": 1,
"self": 0.4894694049999089,
"children": {
"run_training.setup": {
"total": 0.12428436100003637,
"count": 1,
"self": 0.12428436100003637
},
"TrainerController.start_learning": {
"total": 4755.739476973,
"count": 1,
"self": 5.625859534953634,
"children": {
"TrainerController._reset_env": {
"total": 9.297061487999997,
"count": 1,
"self": 9.297061487999997
},
"TrainerController.advance": {
"total": 4740.681414224047,
"count": 181872,
"self": 3.008039972023653,
"children": {
"env_step": {
"total": 4737.673374252024,
"count": 181872,
"self": 3413.4625891710775,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1321.3124972350076,
"count": 181872,
"self": 22.262629374982907,
"children": {
"TorchPolicy.evaluate": {
"total": 1299.0498678600247,
"count": 181872,
"self": 1299.0498678600247
}
}
},
"workers": {
"total": 2.898287845938796,
"count": 181872,
"self": 0.0,
"children": {
"worker_root": {
"total": 4740.419833239913,
"count": 181872,
"is_parallel": true,
"self": 2217.618901365954,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004795546000025297,
"count": 1,
"is_parallel": true,
"self": 0.0033656929999779095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014298530000473875,
"count": 10,
"is_parallel": true,
"self": 0.0014298530000473875
}
}
},
"UnityEnvironment.step": {
"total": 0.03982579500001293,
"count": 1,
"is_parallel": true,
"self": 0.0005936730000257739,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039508899999418645,
"count": 1,
"is_parallel": true,
"self": 0.00039508899999418645
},
"communicator.exchange": {
"total": 0.03689091600000438,
"count": 1,
"is_parallel": true,
"self": 0.03689091600000438
},
"steps_from_proto": {
"total": 0.0019461169999885897,
"count": 1,
"is_parallel": true,
"self": 0.0004080199999521028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015380970000364869,
"count": 10,
"is_parallel": true,
"self": 0.0015380970000364869
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2522.8009318739587,
"count": 181871,
"is_parallel": true,
"self": 98.91521937688776,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 54.818841496126026,
"count": 181871,
"is_parallel": true,
"self": 54.818841496126026
},
"communicator.exchange": {
"total": 2039.0793165449586,
"count": 181871,
"is_parallel": true,
"self": 2039.0793165449586
},
"steps_from_proto": {
"total": 329.9875544559866,
"count": 181871,
"is_parallel": true,
"self": 66.13141579426156,
"children": {
"_process_rank_one_or_two_observation": {
"total": 263.856138661725,
"count": 1818710,
"is_parallel": true,
"self": 263.856138661725
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002583129999038647,
"count": 1,
"self": 0.0002583129999038647,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 4704.872874138866,
"count": 4218257,
"is_parallel": true,
"self": 104.16499749456852,
"children": {
"process_trajectory": {
"total": 2613.9610700512867,
"count": 4218257,
"is_parallel": true,
"self": 2602.5526623962874,
"children": {
"RLTrainer._checkpoint": {
"total": 11.408407654999507,
"count": 40,
"is_parallel": true,
"self": 11.408407654999507
}
}
},
"_update_policy": {
"total": 1986.7468065930102,
"count": 909,
"is_parallel": true,
"self": 729.5694493010133,
"children": {
"TorchPPOOptimizer.update": {
"total": 1257.177357291997,
"count": 46344,
"is_parallel": true,
"self": 1257.177357291997
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13488341299944295,
"count": 1,
"self": 0.0009012330001496593,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1339821799992933,
"count": 1,
"self": 0.1339821799992933
}
}
}
}
}
}
}