sha-abhishek's picture
First Push
a8fb268 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8403844237327576,
"min": 0.8403844237327576,
"max": 2.8738884925842285,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8023.990234375,
"min": 8023.990234375,
"max": 29431.4921875,
"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": 12.9299955368042,
"min": 0.2741631865501404,
"max": 12.955891609191895,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2521.34912109375,
"min": 53.187660217285156,
"max": 2643.37353515625,
"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": 0.07462794158959249,
"min": 0.0625758619568717,
"max": 0.07462794158959249,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29851176635836996,
"min": 0.2503034478274868,
"max": 0.3636253121803034,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1814734480325498,
"min": 0.11824645457204941,
"max": 0.3119646099268221,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7258937921301992,
"min": 0.47298581828819763,
"max": 1.5598230496341106,
"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": 25.295454545454547,
"min": 3.0454545454545454,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 134.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.0454545454545454,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 134.0,
"max": 1407.0,
"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": "1720798822",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720799284"
},
"total": 462.41529091300004,
"count": 1,
"self": 0.43838770100001057,
"children": {
"run_training.setup": {
"total": 0.059002365999958784,
"count": 1,
"self": 0.059002365999958784
},
"TrainerController.start_learning": {
"total": 461.91790084600007,
"count": 1,
"self": 0.6001255389879816,
"children": {
"TrainerController._reset_env": {
"total": 2.868510022999999,
"count": 1,
"self": 2.868510022999999
},
"TrainerController.advance": {
"total": 458.360797773012,
"count": 18201,
"self": 0.2822125669950992,
"children": {
"env_step": {
"total": 458.0785852060169,
"count": 18201,
"self": 297.13216870002213,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.65704312299818,
"count": 18201,
"self": 1.494141649001108,
"children": {
"TorchPolicy.evaluate": {
"total": 159.16290147399707,
"count": 18201,
"self": 159.16290147399707
}
}
},
"workers": {
"total": 0.28937338299658677,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.69038701797376,
"count": 18201,
"is_parallel": true,
"self": 233.20182610898337,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010328183999945395,
"count": 1,
"is_parallel": true,
"self": 0.008791266000116593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015369179998288018,
"count": 10,
"is_parallel": true,
"self": 0.0015369179998288018
}
}
},
"UnityEnvironment.step": {
"total": 0.04342112199992698,
"count": 1,
"is_parallel": true,
"self": 0.0006776789999776156,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043813199999931385,
"count": 1,
"is_parallel": true,
"self": 0.00043813199999931385
},
"communicator.exchange": {
"total": 0.040173863999939385,
"count": 1,
"is_parallel": true,
"self": 0.040173863999939385
},
"steps_from_proto": {
"total": 0.0021314470000106667,
"count": 1,
"is_parallel": true,
"self": 0.00036337599988200964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001768071000128657,
"count": 10,
"is_parallel": true,
"self": 0.001768071000128657
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.4885609089904,
"count": 18200,
"is_parallel": true,
"self": 10.298578634019009,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.514800238985458,
"count": 18200,
"is_parallel": true,
"self": 5.514800238985458
},
"communicator.exchange": {
"total": 177.62693819299045,
"count": 18200,
"is_parallel": true,
"self": 177.62693819299045
},
"steps_from_proto": {
"total": 34.048243842995475,
"count": 18200,
"is_parallel": true,
"self": 6.555672206012218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.492571636983257,
"count": 182000,
"is_parallel": true,
"self": 27.492571636983257
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012302000004638103,
"count": 1,
"self": 0.00012302000004638103,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.8798818779302,
"count": 665033,
"is_parallel": true,
"self": 14.677187324986107,
"children": {
"process_trajectory": {
"total": 250.70985234994453,
"count": 665033,
"is_parallel": true,
"self": 249.82766836194446,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8821839880000653,
"count": 4,
"is_parallel": true,
"self": 0.8821839880000653
}
}
},
"_update_policy": {
"total": 187.49284220299955,
"count": 90,
"is_parallel": true,
"self": 57.20821106500398,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.28463113799558,
"count": 4587,
"is_parallel": true,
"self": 130.28463113799558
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08834449100004349,
"count": 1,
"self": 0.0009442070002023684,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08740028399984112,
"count": 1,
"self": 0.08740028399984112
}
}
}
}
}
}
}