abhishekpradhan's picture
First Push
7b21cf9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.807722806930542,
"min": 0.807722806930542,
"max": 2.8394460678100586,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7676.59765625,
"min": 7676.59765625,
"max": 28985.064453125,
"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": 12.113988876342773,
"min": 0.351755291223526,
"max": 12.113988876342773,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2362.227783203125,
"min": 68.24052429199219,
"max": 2447.7998046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06478984027304321,
"min": 0.06231906672174399,
"max": 0.07682910547979797,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25915936109217286,
"min": 0.24927626688697596,
"max": 0.3722228518942275,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18300121482096465,
"min": 0.13105251090646738,
"max": 0.2744022275887284,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7320048592838586,
"min": 0.5242100436258695,
"max": 1.372011137943642,
"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": 24.295454545454547,
"min": 3.409090909090909,
"max": 24.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1069.0,
"min": 150.0,
"max": 1299.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.295454545454547,
"min": 3.409090909090909,
"max": 24.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1069.0,
"min": 150.0,
"max": 1299.0,
"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": "1742035254",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742035683"
},
"total": 428.513710136,
"count": 1,
"self": 0.4383537720000277,
"children": {
"run_training.setup": {
"total": 0.023491158000069845,
"count": 1,
"self": 0.023491158000069845
},
"TrainerController.start_learning": {
"total": 428.0518652059999,
"count": 1,
"self": 0.3424345909929798,
"children": {
"TrainerController._reset_env": {
"total": 3.4102303540000776,
"count": 1,
"self": 3.4102303540000776
},
"TrainerController.advance": {
"total": 424.21494691400665,
"count": 18192,
"self": 0.3520491059962296,
"children": {
"env_step": {
"total": 302.3753450320089,
"count": 18192,
"self": 230.84265483102797,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.32359879999649,
"count": 18192,
"self": 1.2612549329937792,
"children": {
"TorchPolicy.evaluate": {
"total": 70.06234386700271,
"count": 18192,
"self": 70.06234386700271
}
}
},
"workers": {
"total": 0.20909140098444823,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.5809618860019,
"count": 18192,
"is_parallel": true,
"self": 223.75738179800874,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006235983000010492,
"count": 1,
"is_parallel": true,
"self": 0.004036356000028718,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002199626999981774,
"count": 10,
"is_parallel": true,
"self": 0.002199626999981774
}
}
},
"UnityEnvironment.step": {
"total": 0.034245253999984016,
"count": 1,
"is_parallel": true,
"self": 0.0006765180000911641,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043943799994394794,
"count": 1,
"is_parallel": true,
"self": 0.00043943799994394794
},
"communicator.exchange": {
"total": 0.031107724999969832,
"count": 1,
"is_parallel": true,
"self": 0.031107724999969832
},
"steps_from_proto": {
"total": 0.002021572999979071,
"count": 1,
"is_parallel": true,
"self": 0.00034628699995664647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016752860000224246,
"count": 10,
"is_parallel": true,
"self": 0.0016752860000224246
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.82358008799315,
"count": 18191,
"is_parallel": true,
"self": 9.650715022998043,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.426373294999621,
"count": 18191,
"is_parallel": true,
"self": 5.426373294999621
},
"communicator.exchange": {
"total": 155.74047279299634,
"count": 18191,
"is_parallel": true,
"self": 155.74047279299634
},
"steps_from_proto": {
"total": 32.006018976999144,
"count": 18191,
"is_parallel": true,
"self": 5.7152198949407875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.290799082058356,
"count": 181910,
"is_parallel": true,
"self": 26.290799082058356
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.48755277600151,
"count": 18192,
"self": 0.40906102798351185,
"children": {
"process_trajectory": {
"total": 26.822011273017438,
"count": 18192,
"self": 26.23371885201766,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5882924209997782,
"count": 4,
"self": 0.5882924209997782
}
}
},
"_update_policy": {
"total": 94.25648047500056,
"count": 90,
"self": 37.66936028499083,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.58712019000973,
"count": 4587,
"self": 56.58712019000973
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.130001217272365e-07,
"count": 1,
"self": 9.130001217272365e-07
},
"TrainerController._save_models": {
"total": 0.08425243400006366,
"count": 1,
"self": 0.0009368979999635485,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08331553600010011,
"count": 1,
"self": 0.08331553600010011
}
}
}
}
}
}
}