Tejas-Anvekar's picture
First Push
632fe0f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.1892787218093872,
"min": 0.17429079115390778,
"max": 2.5062944889068604,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 1948.813720703125,
"min": 1747.66357421875,
"max": 25584.25390625,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.892999649047852,
"min": 0.6218810081481934,
"max": 12.908041954040527,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2630.171875,
"min": 120.6449203491211,
"max": 2631.685546875,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0667295840822215,
"min": 0.06470186598883576,
"max": 0.07442767904435374,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3336479204111075,
"min": 0.25880746395534304,
"max": 0.3630236733730699,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.355416145482484,
"min": 0.29208322325173547,
"max": 0.7383754050030428,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.77708072741242,
"min": 1.2457286264774774,
"max": 3.6918770250152138,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0576098237333326e-05,
"min": 1.0576098237333326e-05,
"max": 0.0005891760018039999,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.288049118666663e-05,
"min": 5.288049118666663e-05,
"max": 0.0028468800255199997,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.11410133333333332,
"min": 0.11410133333333332,
"max": 0.8855679999999999,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5705066666666666,
"min": 0.5620053333333335,
"max": 4.29584,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 8.033039999999997e-05,
"min": 8.033039999999997e-05,
"max": 0.003928020400000001,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00040165199999999985,
"min": 0.00040165199999999985,
"max": 0.018981752000000005,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.254545454545454,
"min": 2.977272727272727,
"max": 25.431818181818183,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1389.0,
"min": 131.0,
"max": 1389.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.254545454545454,
"min": 2.977272727272727,
"max": 25.431818181818183,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1389.0,
"min": 131.0,
"max": 1389.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1765393890",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/miniconda/envs/mlagents_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765394562"
},
"total": 672.2297388710003,
"count": 1,
"self": 0.6483824330007337,
"children": {
"run_training.setup": {
"total": 0.019718303000445303,
"count": 1,
"self": 0.019718303000445303
},
"TrainerController.start_learning": {
"total": 671.5616381349992,
"count": 1,
"self": 0.4727465420828594,
"children": {
"TrainerController._reset_env": {
"total": 1.9362923909993697,
"count": 1,
"self": 1.9362923909993697
},
"TrainerController.advance": {
"total": 669.0366719249168,
"count": 27328,
"self": 0.4879455358550331,
"children": {
"env_step": {
"total": 445.67798837295595,
"count": 27328,
"self": 349.49148932098615,
"children": {
"SubprocessEnvManager._take_step": {
"total": 95.89760286805449,
"count": 27328,
"self": 1.744497870113264,
"children": {
"TorchPolicy.evaluate": {
"total": 94.15310499794123,
"count": 27328,
"self": 94.15310499794123
}
}
},
"workers": {
"total": 0.2888961839153126,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 668.6310046399249,
"count": 27328,
"is_parallel": true,
"self": 360.17248974084123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019248910002716002,
"count": 1,
"is_parallel": true,
"self": 0.0005814340001961682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001343457000075432,
"count": 10,
"is_parallel": true,
"self": 0.001343457000075432
}
}
},
"UnityEnvironment.step": {
"total": 0.0342233600003965,
"count": 1,
"is_parallel": true,
"self": 0.0005515419998118887,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004190700001345249,
"count": 1,
"is_parallel": true,
"self": 0.0004190700001345249
},
"communicator.exchange": {
"total": 0.03147531600006914,
"count": 1,
"is_parallel": true,
"self": 0.03147531600006914
},
"steps_from_proto": {
"total": 0.0017774320003809407,
"count": 1,
"is_parallel": true,
"self": 0.0003432140010772855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014342179993036552,
"count": 10,
"is_parallel": true,
"self": 0.0014342179993036552
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 308.45851489908364,
"count": 27327,
"is_parallel": true,
"self": 14.77071552511461,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.733226724989436,
"count": 27327,
"is_parallel": true,
"self": 7.733226724989436
},
"communicator.exchange": {
"total": 235.5809067450491,
"count": 27327,
"is_parallel": true,
"self": 235.5809067450491
},
"steps_from_proto": {
"total": 50.37366590393049,
"count": 27327,
"is_parallel": true,
"self": 9.25405261204105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.119613291889436,
"count": 273270,
"is_parallel": true,
"self": 41.119613291889436
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 222.87073801610586,
"count": 27328,
"self": 0.553346743059592,
"children": {
"process_trajectory": {
"total": 42.27711047703542,
"count": 27328,
"self": 37.25585253603549,
"children": {
"RLTrainer._checkpoint": {
"total": 5.021257940999931,
"count": 60,
"self": 5.021257940999931
}
}
},
"_update_policy": {
"total": 180.04028079601085,
"count": 136,
"self": 73.07994484512255,
"children": {
"TorchPPOOptimizer.update": {
"total": 106.9603359508883,
"count": 9244,
"self": 106.9603359508883
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6949998098425567e-06,
"count": 1,
"self": 1.6949998098425567e-06
},
"TrainerController._save_models": {
"total": 0.1159255820002727,
"count": 1,
"self": 0.001142582999818842,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11478299900045386,
"count": 1,
"self": 0.11478299900045386
}
}
}
}
}
}
}