Emericzhito's picture
First Push
dff4931 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1216928958892822,
"min": 1.1216928958892822,
"max": 2.864833116531372,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10709.923828125,
"min": 10709.923828125,
"max": 29307.2421875,
"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": 12.226785659790039,
"min": 0.339835524559021,
"max": 12.231796264648438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2384.22314453125,
"min": 65.92809295654297,
"max": 2495.286376953125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.067714587084101,
"min": 0.05986425859794276,
"max": 0.07437257954452613,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.270858348336404,
"min": 0.23945703439177105,
"max": 0.36532688653182155,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2106723806583414,
"min": 0.1132573190740967,
"max": 0.26756281624822054,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8426895226333656,
"min": 0.4530292762963868,
"max": 1.3378140812411028,
"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": 24.045454545454547,
"min": 3.4318181818181817,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1058.0,
"min": 151.0,
"max": 1331.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.045454545454547,
"min": 3.4318181818181817,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1058.0,
"min": 151.0,
"max": 1331.0,
"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": "1723516548",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723517086"
},
"total": 538.2248620989999,
"count": 1,
"self": 0.6672067969998352,
"children": {
"run_training.setup": {
"total": 0.06796715900009076,
"count": 1,
"self": 0.06796715900009076
},
"TrainerController.start_learning": {
"total": 537.489688143,
"count": 1,
"self": 0.7509141409962012,
"children": {
"TrainerController._reset_env": {
"total": 3.1532645380000304,
"count": 1,
"self": 3.1532645380000304
},
"TrainerController.advance": {
"total": 533.471021127004,
"count": 18201,
"self": 0.3544092330005242,
"children": {
"env_step": {
"total": 533.1166118940034,
"count": 18201,
"self": 350.9828655129977,
"children": {
"SubprocessEnvManager._take_step": {
"total": 181.76761471800592,
"count": 18201,
"self": 1.8151994600214039,
"children": {
"TorchPolicy.evaluate": {
"total": 179.9524152579845,
"count": 18201,
"self": 179.9524152579845
}
}
},
"workers": {
"total": 0.3661316629998055,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 535.9288266399919,
"count": 18201,
"is_parallel": true,
"self": 265.6644684509854,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006247583000003942,
"count": 1,
"is_parallel": true,
"self": 0.004354560999672685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001893022000331257,
"count": 10,
"is_parallel": true,
"self": 0.001893022000331257
}
}
},
"UnityEnvironment.step": {
"total": 0.04004923900015456,
"count": 1,
"is_parallel": true,
"self": 0.0007266909999543714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000402642000153719,
"count": 1,
"is_parallel": true,
"self": 0.000402642000153719
},
"communicator.exchange": {
"total": 0.036596777000113434,
"count": 1,
"is_parallel": true,
"self": 0.036596777000113434
},
"steps_from_proto": {
"total": 0.002323128999933033,
"count": 1,
"is_parallel": true,
"self": 0.0004138919998695201,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019092370000635128,
"count": 10,
"is_parallel": true,
"self": 0.0019092370000635128
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 270.26435818900654,
"count": 18200,
"is_parallel": true,
"self": 12.338218132004158,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.255133759996852,
"count": 18200,
"is_parallel": true,
"self": 6.255133759996852
},
"communicator.exchange": {
"total": 212.21706365299337,
"count": 18200,
"is_parallel": true,
"self": 212.21706365299337
},
"steps_from_proto": {
"total": 39.45394264401216,
"count": 18200,
"is_parallel": true,
"self": 7.598314228924892,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.855628415087267,
"count": 182000,
"is_parallel": true,
"self": 31.855628415087267
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000170068999977957,
"count": 1,
"self": 0.000170068999977957,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 526.6420750310656,
"count": 794259,
"is_parallel": true,
"self": 17.366099431933662,
"children": {
"process_trajectory": {
"total": 291.98569343213194,
"count": 794259,
"is_parallel": true,
"self": 290.9362745491319,
"children": {
"RLTrainer._checkpoint": {
"total": 1.049418883000044,
"count": 4,
"is_parallel": true,
"self": 1.049418883000044
}
}
},
"_update_policy": {
"total": 217.290282167,
"count": 90,
"is_parallel": true,
"self": 68.90006800999822,
"children": {
"TorchPPOOptimizer.update": {
"total": 148.39021415700176,
"count": 4587,
"is_parallel": true,
"self": 148.39021415700176
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11431826799980627,
"count": 1,
"self": 0.001067082999725244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11325118500008102,
"count": 1,
"self": 0.11325118500008102
}
}
}
}
}
}
}