jimmyofdoom's picture
First Push
f61670e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9444710612297058,
"min": 0.9444710612297058,
"max": 2.8734164237976074,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8997.03125,
"min": 8997.03125,
"max": 29489.873046875,
"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": 12.58355712890625,
"min": 0.31422165036201477,
"max": 12.58355712890625,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2453.793701171875,
"min": 60.95899963378906,
"max": 2549.7705078125,
"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": 0.07354139209572025,
"min": 0.06092971261481152,
"max": 0.0757041191791136,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.294165568382881,
"min": 0.25209531125808865,
"max": 0.3653311331170913,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18219194904554123,
"min": 0.10364136390168878,
"max": 0.2994149215665518,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7287677961821649,
"min": 0.4145654556067551,
"max": 1.497074607832759,
"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": 24.636363636363637,
"min": 2.7954545454545454,
"max": 25.12727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1084.0,
"min": 123.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.636363636363637,
"min": 2.7954545454545454,
"max": 25.12727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1084.0,
"min": 123.0,
"max": 1382.0,
"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": "1692768479",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692768969"
},
"total": 489.76877001699995,
"count": 1,
"self": 0.43517344099973343,
"children": {
"run_training.setup": {
"total": 0.04466507100005401,
"count": 1,
"self": 0.04466507100005401
},
"TrainerController.start_learning": {
"total": 489.28893150500016,
"count": 1,
"self": 0.5467755930048952,
"children": {
"TrainerController._reset_env": {
"total": 4.267854929999999,
"count": 1,
"self": 4.267854929999999
},
"TrainerController.advance": {
"total": 484.33368972099527,
"count": 18200,
"self": 0.2841677359986079,
"children": {
"env_step": {
"total": 484.04952198499666,
"count": 18200,
"self": 352.92061868597034,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.84002776802606,
"count": 18200,
"self": 1.7697394190330442,
"children": {
"TorchPolicy.evaluate": {
"total": 129.07028834899302,
"count": 18200,
"self": 129.07028834899302
}
}
},
"workers": {
"total": 0.288875531000258,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 487.73365952298616,
"count": 18200,
"is_parallel": true,
"self": 230.80800050698497,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005682381999918107,
"count": 1,
"is_parallel": true,
"self": 0.004091037000080178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015913449998379292,
"count": 10,
"is_parallel": true,
"self": 0.0015913449998379292
}
}
},
"UnityEnvironment.step": {
"total": 0.048377590999962194,
"count": 1,
"is_parallel": true,
"self": 0.0006178049999334689,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040605100002721883,
"count": 1,
"is_parallel": true,
"self": 0.00040605100002721883
},
"communicator.exchange": {
"total": 0.04485332900003414,
"count": 1,
"is_parallel": true,
"self": 0.04485332900003414
},
"steps_from_proto": {
"total": 0.00250040599996737,
"count": 1,
"is_parallel": true,
"self": 0.00044972600005621644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020506799999111536,
"count": 10,
"is_parallel": true,
"self": 0.0020506799999111536
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 256.9256590160012,
"count": 18199,
"is_parallel": true,
"self": 10.934109693998494,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.416188233026105,
"count": 18199,
"is_parallel": true,
"self": 5.416188233026105
},
"communicator.exchange": {
"total": 203.00121915997306,
"count": 18199,
"is_parallel": true,
"self": 203.00121915997306
},
"steps_from_proto": {
"total": 37.57414192900353,
"count": 18199,
"is_parallel": true,
"self": 6.892890698989504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.681251230014027,
"count": 181990,
"is_parallel": true,
"self": 30.681251230014027
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011334099986015644,
"count": 1,
"self": 0.00011334099986015644,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 480.4501829669575,
"count": 448872,
"is_parallel": true,
"self": 10.402804919979758,
"children": {
"process_trajectory": {
"total": 262.6355932819773,
"count": 448872,
"is_parallel": true,
"self": 261.2954430599772,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3401502220001476,
"count": 4,
"is_parallel": true,
"self": 1.3401502220001476
}
}
},
"_update_policy": {
"total": 207.41178476500045,
"count": 90,
"is_parallel": true,
"self": 83.71399589399562,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.69778887100483,
"count": 4587,
"is_parallel": true,
"self": 123.69778887100483
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1404979200001435,
"count": 1,
"self": 0.0008362580001630704,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13966166199998042,
"count": 1,
"self": 0.13966166199998042
}
}
}
}
}
}
}