ckandemir's picture
First Push
3c866ec
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9918124079704285,
"min": 0.9918124079704285,
"max": 2.85380220413208,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9502.5546875,
"min": 9502.5546875,
"max": 29319.96484375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.804975509643555,
"min": 0.31755757331848145,
"max": 12.804975509643555,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2496.97021484375,
"min": 61.606170654296875,
"max": 2595.9921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0718540029647913,
"min": 0.06346121619577638,
"max": 0.07507280600725161,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2874160118591652,
"min": 0.26357851564135476,
"max": 0.3658167543745709,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21041550523802344,
"min": 0.11804096123052979,
"max": 0.2917809882292561,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8416620209520937,
"min": 0.47216384492211916,
"max": 1.3984633184531154,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.613636363636363,
"min": 3.159090909090909,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 139.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.159090909090909,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 139.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691963857",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1691964271"
},
"total": 414.04300997300015,
"count": 1,
"self": 0.3253583749997233,
"children": {
"run_training.setup": {
"total": 0.05955182400020931,
"count": 1,
"self": 0.05955182400020931
},
"TrainerController.start_learning": {
"total": 413.6580997740002,
"count": 1,
"self": 0.6742156350301229,
"children": {
"TrainerController._reset_env": {
"total": 1.1406543110001621,
"count": 1,
"self": 1.1406543110001621
},
"TrainerController.advance": {
"total": 411.68885380796974,
"count": 18207,
"self": 0.2847163629676288,
"children": {
"env_step": {
"total": 411.4041374450021,
"count": 18207,
"self": 322.3470492489746,
"children": {
"SubprocessEnvManager._take_step": {
"total": 88.75644919802971,
"count": 18207,
"self": 1.6263914300438955,
"children": {
"TorchPolicy.evaluate": {
"total": 87.13005776798582,
"count": 18207,
"self": 87.13005776798582
}
}
},
"workers": {
"total": 0.3006389979977939,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.7721411670168,
"count": 18207,
"is_parallel": true,
"self": 195.25249210804805,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002390323999861721,
"count": 1,
"is_parallel": true,
"self": 0.0007085319989528216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016817920009088994,
"count": 10,
"is_parallel": true,
"self": 0.0016817920009088994
}
}
},
"UnityEnvironment.step": {
"total": 0.030444258999978047,
"count": 1,
"is_parallel": true,
"self": 0.00048480100031156326,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031575200000588666,
"count": 1,
"is_parallel": true,
"self": 0.00031575200000588666
},
"communicator.exchange": {
"total": 0.028064401999927213,
"count": 1,
"is_parallel": true,
"self": 0.028064401999927213
},
"steps_from_proto": {
"total": 0.0015793039997333835,
"count": 1,
"is_parallel": true,
"self": 0.00035033699896303006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012289670007703535,
"count": 10,
"is_parallel": true,
"self": 0.0012289670007703535
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.51964905896875,
"count": 18206,
"is_parallel": true,
"self": 7.4317913398977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.215054619045532,
"count": 18206,
"is_parallel": true,
"self": 4.215054619045532
},
"communicator.exchange": {
"total": 179.89068704898682,
"count": 18206,
"is_parallel": true,
"self": 179.89068704898682
},
"steps_from_proto": {
"total": 25.9821160510387,
"count": 18206,
"is_parallel": true,
"self": 5.475723512999593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 20.50639253803911,
"count": 182060,
"is_parallel": true,
"self": 20.50639253803911
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020111699996050447,
"count": 1,
"self": 0.00020111699996050447,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 410.6551612760845,
"count": 194418,
"is_parallel": true,
"self": 4.146439071206714,
"children": {
"process_trajectory": {
"total": 225.67163409587738,
"count": 194418,
"is_parallel": true,
"self": 224.7010320478771,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9706020480002735,
"count": 4,
"is_parallel": true,
"self": 0.9706020480002735
}
}
},
"_update_policy": {
"total": 180.83708810900043,
"count": 90,
"is_parallel": true,
"self": 50.76980555899445,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.06728255000598,
"count": 4587,
"is_parallel": true,
"self": 130.06728255000598
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15417490300023928,
"count": 1,
"self": 0.0009586560004208877,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1532162469998184,
"count": 1,
"self": 0.1532162469998184
}
}
}
}
}
}
}