Farrukh42's picture
First Push
616cc8c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9026537537574768,
"min": 0.9026537537574768,
"max": 2.8514537811279297,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8578.8212890625,
"min": 8578.8212890625,
"max": 29107.640625,
"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": 12.370770454406738,
"min": 0.3398783206939697,
"max": 12.370770454406738,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2412.30029296875,
"min": 65.93639373779297,
"max": 2504.80810546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0670540410621256,
"min": 0.058205959980898794,
"max": 0.07765681804705632,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2682161642485024,
"min": 0.23282383992359518,
"max": 0.36511973805460785,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18506517867539443,
"min": 0.10609271054329605,
"max": 0.2685551171793657,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7402607147015777,
"min": 0.4243708421731842,
"max": 1.3427755858968284,
"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.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.Environment.CumulativeReward.mean": {
"value": 23.65909090909091,
"min": 3.0454545454545454,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1041.0,
"min": 134.0,
"max": 1343.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.65909090909091,
"min": 3.0454545454545454,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1041.0,
"min": 134.0,
"max": 1343.0,
"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": "1752933303",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752933729"
},
"total": 426.03030077100004,
"count": 1,
"self": 0.4330418690000215,
"children": {
"run_training.setup": {
"total": 0.022858424999981253,
"count": 1,
"self": 0.022858424999981253
},
"TrainerController.start_learning": {
"total": 425.57440047700004,
"count": 1,
"self": 0.33973459898220426,
"children": {
"TrainerController._reset_env": {
"total": 3.0686776369999507,
"count": 1,
"self": 3.0686776369999507
},
"TrainerController.advance": {
"total": 422.08449434001795,
"count": 18192,
"self": 0.37068365401012215,
"children": {
"env_step": {
"total": 305.35364611200873,
"count": 18192,
"self": 235.36344896501964,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.77943124499507,
"count": 18192,
"self": 1.2447726750031052,
"children": {
"TorchPolicy.evaluate": {
"total": 68.53465856999196,
"count": 18192,
"self": 68.53465856999196
}
}
},
"workers": {
"total": 0.2107659019940229,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.17553414799283,
"count": 18192,
"is_parallel": true,
"self": 216.93107221199807,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004735890000006293,
"count": 1,
"is_parallel": true,
"self": 0.003325697000036598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001410192999969695,
"count": 10,
"is_parallel": true,
"self": 0.001410192999969695
}
}
},
"UnityEnvironment.step": {
"total": 0.0375330719999738,
"count": 1,
"is_parallel": true,
"self": 0.0006048439998949107,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039709299994683533,
"count": 1,
"is_parallel": true,
"self": 0.00039709299994683533
},
"communicator.exchange": {
"total": 0.03463401800001975,
"count": 1,
"is_parallel": true,
"self": 0.03463401800001975
},
"steps_from_proto": {
"total": 0.0018971170001123028,
"count": 1,
"is_parallel": true,
"self": 0.0003619540001409405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015351629999713623,
"count": 10,
"is_parallel": true,
"self": 0.0015351629999713623
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.24446193599476,
"count": 18191,
"is_parallel": true,
"self": 9.707184034997908,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.472256226002855,
"count": 18191,
"is_parallel": true,
"self": 5.472256226002855
},
"communicator.exchange": {
"total": 159.98794484799316,
"count": 18191,
"is_parallel": true,
"self": 159.98794484799316
},
"steps_from_proto": {
"total": 32.07707682700084,
"count": 18191,
"is_parallel": true,
"self": 5.762979553966034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.314097273034804,
"count": 181910,
"is_parallel": true,
"self": 26.314097273034804
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.3601645739991,
"count": 18192,
"self": 0.43902109798921174,
"children": {
"process_trajectory": {
"total": 25.98056340501023,
"count": 18192,
"self": 25.583189897010243,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39737350799998694,
"count": 4,
"self": 0.39737350799998694
}
}
},
"_update_policy": {
"total": 89.94058007099966,
"count": 90,
"self": 36.940711341996234,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.999868729003424,
"count": 4587,
"self": 52.999868729003424
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0930000371445203e-06,
"count": 1,
"self": 1.0930000371445203e-06
},
"TrainerController._save_models": {
"total": 0.08149280799989356,
"count": 1,
"self": 0.000834385999951337,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08065842199994222,
"count": 1,
"self": 0.08065842199994222
}
}
}
}
}
}
}