issam-block's picture
First Push
a8d0446 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8563681244850159,
"min": 0.8468152284622192,
"max": 2.8360354900360107,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8138.9228515625,
"min": 8138.9228515625,
"max": 28950.25,
"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": 11.920008659362793,
"min": 0.43334299325942993,
"max": 11.920008659362793,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2324.401611328125,
"min": 84.06854248046875,
"max": 2419.694580078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06996752626112619,
"min": 0.06319915721157003,
"max": 0.07322890803762301,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27987010504450477,
"min": 0.2527966288462801,
"max": 0.35655296793579594,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1733860357061905,
"min": 0.13213152115064325,
"max": 0.2752797464821853,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.693544142824762,
"min": 0.528526084602573,
"max": 1.3368686767769795,
"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": 22.886363636363637,
"min": 3.6363636363636362,
"max": 23.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1007.0,
"min": 160.0,
"max": 1316.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.886363636363637,
"min": 3.6363636363636362,
"max": 23.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1007.0,
"min": 160.0,
"max": 1316.0,
"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": "1752422536",
"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": "1752422974"
},
"total": 437.838788051,
"count": 1,
"self": 0.43450053199995864,
"children": {
"run_training.setup": {
"total": 0.02919238399999813,
"count": 1,
"self": 0.02919238399999813
},
"TrainerController.start_learning": {
"total": 437.37509513500004,
"count": 1,
"self": 0.4143602789980605,
"children": {
"TrainerController._reset_env": {
"total": 3.2428904099999727,
"count": 1,
"self": 3.2428904099999727
},
"TrainerController.advance": {
"total": 433.636257241002,
"count": 18192,
"self": 0.39979037800668493,
"children": {
"env_step": {
"total": 314.03905145199934,
"count": 18192,
"self": 241.9827739719812,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.82441950200985,
"count": 18192,
"self": 1.314272706002157,
"children": {
"TorchPolicy.evaluate": {
"total": 70.51014679600769,
"count": 18192,
"self": 70.51014679600769
}
}
},
"workers": {
"total": 0.23185797800829278,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.89680024300606,
"count": 18192,
"is_parallel": true,
"self": 223.59049734400747,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005480720000036854,
"count": 1,
"is_parallel": true,
"self": 0.004018260999998802,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014624590000380522,
"count": 10,
"is_parallel": true,
"self": 0.0014624590000380522
}
}
},
"UnityEnvironment.step": {
"total": 0.03732316200000696,
"count": 1,
"is_parallel": true,
"self": 0.0005923649999886038,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005076809999877696,
"count": 1,
"is_parallel": true,
"self": 0.0005076809999877696
},
"communicator.exchange": {
"total": 0.03421958100000211,
"count": 1,
"is_parallel": true,
"self": 0.03421958100000211
},
"steps_from_proto": {
"total": 0.002003535000028478,
"count": 1,
"is_parallel": true,
"self": 0.00041355300004397577,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015899819999845022,
"count": 10,
"is_parallel": true,
"self": 0.0015899819999845022
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.30630289899858,
"count": 18191,
"is_parallel": true,
"self": 10.18287778699937,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.62290178400076,
"count": 18191,
"is_parallel": true,
"self": 5.62290178400076
},
"communicator.exchange": {
"total": 163.42282566899826,
"count": 18191,
"is_parallel": true,
"self": 163.42282566899826
},
"steps_from_proto": {
"total": 33.077697659000194,
"count": 18191,
"is_parallel": true,
"self": 6.07397405400161,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.003723604998584,
"count": 181910,
"is_parallel": true,
"self": 27.003723604998584
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.19741541099597,
"count": 18192,
"self": 0.44991078098735215,
"children": {
"process_trajectory": {
"total": 26.449120946008406,
"count": 18192,
"self": 25.98267231400837,
"children": {
"RLTrainer._checkpoint": {
"total": 0.46644863200003783,
"count": 4,
"self": 0.46644863200003783
}
}
},
"_update_policy": {
"total": 92.29838368400021,
"count": 90,
"self": 37.89976370700424,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.398619976995974,
"count": 4587,
"self": 54.398619976995974
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.689999842521502e-07,
"count": 1,
"self": 9.689999842521502e-07
},
"TrainerController._save_models": {
"total": 0.08158623600002102,
"count": 1,
"self": 0.0008533289999377303,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08073290700008329,
"count": 1,
"self": 0.08073290700008329
}
}
}
}
}
}
}