DumbleDuck's picture
First Push
31ecbf3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0005192756652832,
"min": 1.0005192756652832,
"max": 2.8310415744781494,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8804.5693359375,
"min": 8804.5693359375,
"max": 28940.94921875,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 249880.0,
"min": 9952.0,
"max": 249880.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 249880.0,
"min": 9952.0,
"max": 249880.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.957201957702637,
"min": 0.414703905582428,
"max": 13.957201957702637,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1353.8486328125,
"min": 40.226280212402344,
"max": 1411.627685546875,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.568181818181817,
"min": 4.681818181818182,
"max": 27.568181818181817,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1213.0,
"min": 206.0,
"max": 1515.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.568181818181817,
"min": 4.681818181818182,
"max": 27.568181818181817,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1213.0,
"min": 206.0,
"max": 1515.0,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06210129925617081,
"min": 0.06210129925617081,
"max": 0.07561748272501956,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24840519702468325,
"min": 0.24840519702468325,
"max": 0.3780874136250978,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16262870654463768,
"min": 0.13736278671844332,
"max": 0.2874898902487521,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6505148261785507,
"min": 0.5921700890449917,
"max": 1.4112983188208414,
"count": 25
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.5040098120000011e-05,
"min": 1.5040098120000011e-05,
"max": 0.0007824000022000001,
"count": 25
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.0160392480000045e-05,
"min": 6.0160392480000045e-05,
"max": 0.0037536000308,
"count": 25
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10188,
"min": 0.10188,
"max": 0.1978,
"count": 25
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40752,
"min": 0.40752,
"max": 0.9692000000000001,
"count": 25
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00010381200000000008,
"min": 0.00010381200000000008,
"max": 0.004890220000000001,
"count": 25
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00041524800000000033,
"min": 0.00041524800000000033,
"max": 0.02346308,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1745285894",
"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=SnowballTarget6 --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": "1745286442"
},
"total": 548.207428613,
"count": 1,
"self": 0.8045825750004951,
"children": {
"run_training.setup": {
"total": 0.020663676999902236,
"count": 1,
"self": 0.020663676999902236
},
"TrainerController.start_learning": {
"total": 547.3821823609996,
"count": 1,
"self": 0.4138622600439703,
"children": {
"TrainerController._reset_env": {
"total": 2.1674611489997915,
"count": 1,
"self": 2.1674611489997915
},
"TrainerController.advance": {
"total": 544.6162616379552,
"count": 22728,
"self": 0.4284669310491154,
"children": {
"env_step": {
"total": 375.3740195359478,
"count": 22728,
"self": 275.75270871493376,
"children": {
"SubprocessEnvManager._take_step": {
"total": 99.37057520403687,
"count": 22728,
"self": 1.5869785651102575,
"children": {
"TorchPolicy.evaluate": {
"total": 97.78359663892661,
"count": 22728,
"self": 97.78359663892661
}
}
},
"workers": {
"total": 0.25073561697718105,
"count": 22728,
"self": 0.0,
"children": {
"worker_root": {
"total": 545.300565538897,
"count": 22728,
"is_parallel": true,
"self": 302.92732103581784,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002240064000034181,
"count": 1,
"is_parallel": true,
"self": 0.0006361899995681597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016038740004660212,
"count": 10,
"is_parallel": true,
"self": 0.0016038740004660212
}
}
},
"UnityEnvironment.step": {
"total": 0.05354901500049891,
"count": 1,
"is_parallel": true,
"self": 0.0005499720009538578,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038391399993997766,
"count": 1,
"is_parallel": true,
"self": 0.00038391399993997766
},
"communicator.exchange": {
"total": 0.050935342000229866,
"count": 1,
"is_parallel": true,
"self": 0.050935342000229866
},
"steps_from_proto": {
"total": 0.0016797869993752101,
"count": 1,
"is_parallel": true,
"self": 0.0003143739995721262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001365412999803084,
"count": 10,
"is_parallel": true,
"self": 0.001365412999803084
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.37324450307915,
"count": 22727,
"is_parallel": true,
"self": 11.741168807054237,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.487960024999666,
"count": 22727,
"is_parallel": true,
"self": 6.487960024999666
},
"communicator.exchange": {
"total": 186.05993160305934,
"count": 22727,
"is_parallel": true,
"self": 186.05993160305934
},
"steps_from_proto": {
"total": 38.08418406796591,
"count": 22727,
"is_parallel": true,
"self": 6.759363543805193,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.324820524160714,
"count": 227270,
"is_parallel": true,
"self": 31.324820524160714
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 168.81377517095825,
"count": 22728,
"self": 0.49420756201379845,
"children": {
"process_trajectory": {
"total": 41.260879152942834,
"count": 22728,
"self": 40.4989085239431,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7619706289997339,
"count": 5,
"self": 0.7619706289997339
}
}
},
"_update_policy": {
"total": 127.05868845600162,
"count": 113,
"self": 48.77569470803155,
"children": {
"TorchPPOOptimizer.update": {
"total": 78.28299374797007,
"count": 5763,
"self": 78.28299374797007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.42800035973778e-06,
"count": 1,
"self": 1.42800035973778e-06
},
"TrainerController._save_models": {
"total": 0.18459588600035204,
"count": 1,
"self": 0.0011665820002235705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18342930400012847,
"count": 1,
"self": 0.18342930400012847
}
}
}
}
}
}
}