Anish13's picture
First Push
3ef70df verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7428228855133057,
"min": 0.717578113079071,
"max": 2.866539716720581,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7059.78857421875,
"min": 7059.78857421875,
"max": 29261.63671875,
"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": 13.098311424255371,
"min": 0.42757660150527954,
"max": 13.098311424255371,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.170654296875,
"min": 82.94985961914062,
"max": 2649.773681640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06760587373954717,
"min": 0.06337408943185366,
"max": 0.0766586001451109,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2704234949581887,
"min": 0.25349635772741463,
"max": 0.3832930007255545,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1837115724954535,
"min": 0.10986029506003593,
"max": 0.2910733493519765,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.734846289981814,
"min": 0.4394411802401437,
"max": 1.4553667467598823,
"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": 26.068181818181817,
"min": 3.0681818181818183,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1147.0,
"min": 135.0,
"max": 1430.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.068181818181817,
"min": 3.0681818181818183,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1147.0,
"min": 135.0,
"max": 1430.0,
"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": "1745562529",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745562947"
},
"total": 417.518726234,
"count": 1,
"self": 0.437460248999912,
"children": {
"run_training.setup": {
"total": 0.023300991000041904,
"count": 1,
"self": 0.023300991000041904
},
"TrainerController.start_learning": {
"total": 417.05796499400003,
"count": 1,
"self": 0.32750653200815805,
"children": {
"TrainerController._reset_env": {
"total": 3.846594367000023,
"count": 1,
"self": 3.846594367000023
},
"TrainerController.advance": {
"total": 412.8046588759919,
"count": 18192,
"self": 0.349584537996634,
"children": {
"env_step": {
"total": 290.69862377399824,
"count": 18192,
"self": 221.16686307999646,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.34330368100115,
"count": 18192,
"self": 1.191518034000353,
"children": {
"TorchPolicy.evaluate": {
"total": 68.15178564700079,
"count": 18192,
"self": 68.15178564700079
}
}
},
"workers": {
"total": 0.18845701300062956,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 415.64656797198626,
"count": 18192,
"is_parallel": true,
"self": 221.39742962698278,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005407152999964637,
"count": 1,
"is_parallel": true,
"self": 0.0038787349998870013,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001528418000077636,
"count": 10,
"is_parallel": true,
"self": 0.001528418000077636
}
}
},
"UnityEnvironment.step": {
"total": 0.03593268399998806,
"count": 1,
"is_parallel": true,
"self": 0.0005604510000125629,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041639500000201224,
"count": 1,
"is_parallel": true,
"self": 0.00041639500000201224
},
"communicator.exchange": {
"total": 0.03309667099995295,
"count": 1,
"is_parallel": true,
"self": 0.03309667099995295
},
"steps_from_proto": {
"total": 0.001859167000020534,
"count": 1,
"is_parallel": true,
"self": 0.0003705659999013733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014886010001191607,
"count": 10,
"is_parallel": true,
"self": 0.0014886010001191607
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 194.24913834500347,
"count": 18191,
"is_parallel": true,
"self": 9.553567125990469,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.291109466008436,
"count": 18191,
"is_parallel": true,
"self": 5.291109466008436
},
"communicator.exchange": {
"total": 149.2825601320008,
"count": 18191,
"is_parallel": true,
"self": 149.2825601320008
},
"steps_from_proto": {
"total": 30.121901621003758,
"count": 18191,
"is_parallel": true,
"self": 5.349114095014215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.772787525989543,
"count": 181910,
"is_parallel": true,
"self": 24.772787525989543
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.75645056399702,
"count": 18192,
"self": 0.41610153499442504,
"children": {
"process_trajectory": {
"total": 27.902501650002762,
"count": 18192,
"self": 26.04484837100273,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8576532790000329,
"count": 20,
"self": 1.8576532790000329
}
}
},
"_update_policy": {
"total": 93.43784737899983,
"count": 90,
"self": 37.527226152000424,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.91062122699941,
"count": 4587,
"self": 55.91062122699941
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.689999842521502e-07,
"count": 1,
"self": 9.689999842521502e-07
},
"TrainerController._save_models": {
"total": 0.07920424999997522,
"count": 1,
"self": 0.0008035109999582346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07840073900001698,
"count": 1,
"self": 0.07840073900001698
}
}
}
}
}
}
}