AndreiVoicuT's picture
First Push
9fd9111 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9159056544303894,
"min": 0.882427990436554,
"max": 2.864011287689209,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8704.767578125,
"min": 8464.2490234375,
"max": 29235.826171875,
"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": 13.06135082244873,
"min": 0.32515251636505127,
"max": 13.076583862304688,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2546.96337890625,
"min": 63.079586029052734,
"max": 2667.623046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07307934462854367,
"min": 0.06489892806954838,
"max": 0.07524919898965962,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29231737851417466,
"min": 0.2595957122781935,
"max": 0.3738248242315261,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19551756444807145,
"min": 0.11918051663087681,
"max": 0.28407194414267356,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7820702577922858,
"min": 0.47672206652350724,
"max": 1.3324246096844765,
"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": 25.295454545454547,
"min": 3.5,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 154.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.5,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 154.0,
"max": 1410.0,
"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": "1746871900",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "1746872348"
},
"total": 448.7440762880001,
"count": 1,
"self": 0.43055184099989674,
"children": {
"run_training.setup": {
"total": 0.02311195100014629,
"count": 1,
"self": 0.02311195100014629
},
"TrainerController.start_learning": {
"total": 448.29041249600004,
"count": 1,
"self": 0.3583130690080907,
"children": {
"TrainerController._reset_env": {
"total": 3.1615123719998337,
"count": 1,
"self": 3.1615123719998337
},
"TrainerController.advance": {
"total": 444.68299474299215,
"count": 18192,
"self": 0.39796047697200265,
"children": {
"env_step": {
"total": 317.17415838701777,
"count": 18192,
"self": 242.1564060070093,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.7975182000016,
"count": 18192,
"self": 1.3318065479927554,
"children": {
"TorchPolicy.evaluate": {
"total": 73.46571165200885,
"count": 18192,
"self": 73.46571165200885
}
}
},
"workers": {
"total": 0.22023418000685524,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.8490568429959,
"count": 18192,
"is_parallel": true,
"self": 234.01869881598168,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005578768000077616,
"count": 1,
"is_parallel": true,
"self": 0.004217356999788535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013614110002890811,
"count": 10,
"is_parallel": true,
"self": 0.0013614110002890811
}
}
},
"UnityEnvironment.step": {
"total": 0.07044168099992021,
"count": 1,
"is_parallel": true,
"self": 0.0005901649999486835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004523860000062996,
"count": 1,
"is_parallel": true,
"self": 0.0004523860000062996
},
"communicator.exchange": {
"total": 0.06757478400004402,
"count": 1,
"is_parallel": true,
"self": 0.06757478400004402
},
"steps_from_proto": {
"total": 0.0018243459999212064,
"count": 1,
"is_parallel": true,
"self": 0.0004001499999048974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001424196000016309,
"count": 10,
"is_parallel": true,
"self": 0.001424196000016309
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.8303580270142,
"count": 18191,
"is_parallel": true,
"self": 9.993676580020747,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.82111073400938,
"count": 18191,
"is_parallel": true,
"self": 5.82111073400938
},
"communicator.exchange": {
"total": 163.54507456199235,
"count": 18191,
"is_parallel": true,
"self": 163.54507456199235
},
"steps_from_proto": {
"total": 33.47049615099172,
"count": 18191,
"is_parallel": true,
"self": 5.958633497975143,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.51186265301658,
"count": 181910,
"is_parallel": true,
"self": 27.51186265301658
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.11087587900238,
"count": 18192,
"self": 0.4445558099948812,
"children": {
"process_trajectory": {
"total": 29.114273382007013,
"count": 18192,
"self": 28.623952940007257,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49032044199975644,
"count": 4,
"self": 0.49032044199975644
}
}
},
"_update_policy": {
"total": 97.55204668700048,
"count": 90,
"self": 40.446852947994785,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.1051937390057,
"count": 4587,
"self": 57.1051937390057
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.450000106880907e-07,
"count": 1,
"self": 9.450000106880907e-07
},
"TrainerController._save_models": {
"total": 0.08759136699995906,
"count": 1,
"self": 0.0008284939999612106,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08676287299999785,
"count": 1,
"self": 0.08676287299999785
}
}
}
}
}
}
}