Shivraj8615's picture
First Push
4fa4126
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8315359354019165,
"min": 0.8315359354019165,
"max": 2.8731789588928223,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7994.38671875,
"min": 7994.38671875,
"max": 29424.2265625,
"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": 12.950150489807129,
"min": 0.30350440740585327,
"max": 12.950150489807129,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.279296875,
"min": 58.87985610961914,
"max": 2616.23876953125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07906868881272043,
"min": 0.058885134923797974,
"max": 0.07906868881272043,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3162747552508817,
"min": 0.2443739444178052,
"max": 0.37533863345115426,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21599436682813308,
"min": 0.11358385526246445,
"max": 0.3130761022661247,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8639774673125323,
"min": 0.4543354210498578,
"max": 1.4516710681183373,
"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": 25.5,
"min": 3.090909090909091,
"max": 26.036363636363635,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 136.0,
"max": 1432.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.090909090909091,
"max": 26.036363636363635,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 136.0,
"max": 1432.0,
"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": "1680165604",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1680166081"
},
"total": 477.455573886,
"count": 1,
"self": 0.7857172640000272,
"children": {
"run_training.setup": {
"total": 0.1164616930000193,
"count": 1,
"self": 0.1164616930000193
},
"TrainerController.start_learning": {
"total": 476.553394929,
"count": 1,
"self": 0.5784177989960426,
"children": {
"TrainerController._reset_env": {
"total": 9.979325700999993,
"count": 1,
"self": 9.979325700999993
},
"TrainerController.advance": {
"total": 465.773757830004,
"count": 18217,
"self": 0.28887204700549773,
"children": {
"env_step": {
"total": 465.4848857829985,
"count": 18217,
"self": 336.6330328689819,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.5680786699918,
"count": 18217,
"self": 2.3988774799767043,
"children": {
"TorchPolicy.evaluate": {
"total": 126.16920119001509,
"count": 18217,
"self": 126.16920119001509
}
}
},
"workers": {
"total": 0.2837742440248121,
"count": 18217,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.84263689800036,
"count": 18217,
"is_parallel": true,
"self": 225.5386030759904,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006404824000014742,
"count": 1,
"is_parallel": true,
"self": 0.004822585999932016,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015822380000827252,
"count": 10,
"is_parallel": true,
"self": 0.0015822380000827252
}
}
},
"UnityEnvironment.step": {
"total": 0.04735585099990658,
"count": 1,
"is_parallel": true,
"self": 0.0005899340000041775,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003047679999781394,
"count": 1,
"is_parallel": true,
"self": 0.0003047679999781394
},
"communicator.exchange": {
"total": 0.04455943899995418,
"count": 1,
"is_parallel": true,
"self": 0.04455943899995418
},
"steps_from_proto": {
"total": 0.0019017099999700804,
"count": 1,
"is_parallel": true,
"self": 0.00041813999985151895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014835700001185614,
"count": 10,
"is_parallel": true,
"self": 0.0014835700001185614
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 249.30403382200996,
"count": 18216,
"is_parallel": true,
"self": 9.685487273982176,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.31223666901974,
"count": 18216,
"is_parallel": true,
"self": 5.31223666901974
},
"communicator.exchange": {
"total": 202.48826643601035,
"count": 18216,
"is_parallel": true,
"self": 202.48826643601035
},
"steps_from_proto": {
"total": 31.81804344299769,
"count": 18216,
"is_parallel": true,
"self": 6.373953496992726,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.444089946004965,
"count": 182160,
"is_parallel": true,
"self": 25.444089946004965
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014092099991103169,
"count": 1,
"self": 0.00014092099991103169,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.2888918100788,
"count": 414838,
"is_parallel": true,
"self": 10.180423664095088,
"children": {
"process_trajectory": {
"total": 257.0457963759844,
"count": 414838,
"is_parallel": true,
"self": 255.29354110698466,
"children": {
"RLTrainer._checkpoint": {
"total": 1.752255268999761,
"count": 4,
"is_parallel": true,
"self": 1.752255268999761
}
}
},
"_update_policy": {
"total": 195.06267176999927,
"count": 90,
"is_parallel": true,
"self": 73.10170582399508,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.9609659460042,
"count": 4584,
"is_parallel": true,
"self": 121.9609659460042
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22175267800002985,
"count": 1,
"self": 0.0011939969999730238,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22055868100005682,
"count": 1,
"self": 0.22055868100005682
}
}
}
}
}
}
}