williamcorrias's picture
First Push
980385f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8754200339317322,
"min": 0.8739848732948303,
"max": 2.854846477508545,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8319.9921875,
"min": 8319.9921875,
"max": 29142.2734375,
"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": 12.35877513885498,
"min": 0.28668758273124695,
"max": 12.35877513885498,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2409.961181640625,
"min": 55.617393493652344,
"max": 2493.631591796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07260945552929222,
"min": 0.061717571693959916,
"max": 0.07416814409639211,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2904378221171689,
"min": 0.24687028677583966,
"max": 0.36190116239424025,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20143325692590547,
"min": 0.12894633732160882,
"max": 0.27121445660789806,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8057330277036219,
"min": 0.5157853492864353,
"max": 1.3157456558124692,
"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": 24.045454545454547,
"min": 3.5,
"max": 24.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1058.0,
"min": 154.0,
"max": 1340.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.045454545454547,
"min": 3.5,
"max": 24.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1058.0,
"min": 154.0,
"max": 1340.0,
"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": "1736162968",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736163381"
},
"total": 413.21818772000006,
"count": 1,
"self": 0.47481126400089124,
"children": {
"run_training.setup": {
"total": 0.05489652899996145,
"count": 1,
"self": 0.05489652899996145
},
"TrainerController.start_learning": {
"total": 412.6884799269992,
"count": 1,
"self": 0.3296643119547298,
"children": {
"TrainerController._reset_env": {
"total": 2.049099546000434,
"count": 1,
"self": 2.049099546000434
},
"TrainerController.advance": {
"total": 410.17387525704453,
"count": 18192,
"self": 0.3590669870045531,
"children": {
"env_step": {
"total": 289.04650242504795,
"count": 18192,
"self": 220.2813686119698,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.55850705302873,
"count": 18192,
"self": 1.215420150007958,
"children": {
"TorchPolicy.evaluate": {
"total": 67.34308690302078,
"count": 18192,
"self": 67.34308690302078
}
}
},
"workers": {
"total": 0.20662676004940295,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 411.18755414504085,
"count": 18192,
"is_parallel": true,
"self": 218.4773439542123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002220809999926132,
"count": 1,
"is_parallel": true,
"self": 0.0006899609998072265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015308490001189057,
"count": 10,
"is_parallel": true,
"self": 0.0015308490001189057
}
}
},
"UnityEnvironment.step": {
"total": 0.034312122000301315,
"count": 1,
"is_parallel": true,
"self": 0.0006437830006689182,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003769109998756903,
"count": 1,
"is_parallel": true,
"self": 0.0003769109998756903
},
"communicator.exchange": {
"total": 0.031424693999724695,
"count": 1,
"is_parallel": true,
"self": 0.031424693999724695
},
"steps_from_proto": {
"total": 0.001866734000032011,
"count": 1,
"is_parallel": true,
"self": 0.00035198399655200774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015147500034800032,
"count": 10,
"is_parallel": true,
"self": 0.0015147500034800032
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.71021019082855,
"count": 18191,
"is_parallel": true,
"self": 9.772208454830434,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.317379480949057,
"count": 18191,
"is_parallel": true,
"self": 5.317379480949057
},
"communicator.exchange": {
"total": 146.89627032895805,
"count": 18191,
"is_parallel": true,
"self": 146.89627032895805
},
"steps_from_proto": {
"total": 30.724351926091003,
"count": 18191,
"is_parallel": true,
"self": 5.414571642187184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.30978028390382,
"count": 181910,
"is_parallel": true,
"self": 25.30978028390382
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.76830584499203,
"count": 18192,
"self": 0.381388806893483,
"children": {
"process_trajectory": {
"total": 28.220020826091968,
"count": 18192,
"self": 27.736327316091774,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4836935100001938,
"count": 4,
"self": 0.4836935100001938
}
}
},
"_update_policy": {
"total": 92.16689621200658,
"count": 90,
"self": 37.10395542401966,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.06294078798692,
"count": 4587,
"self": 55.06294078798692
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1909996828762814e-06,
"count": 1,
"self": 1.1909996828762814e-06
},
"TrainerController._save_models": {
"total": 0.13583962099983182,
"count": 1,
"self": 0.001535766000415606,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13430385499941622,
"count": 1,
"self": 0.13430385499941622
}
}
}
}
}
}
}