goforit123's picture
First Push
85662cb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0418444871902466,
"min": 1.0418444871902466,
"max": 2.836660623550415,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9901.6904296875,
"min": 9901.6904296875,
"max": 28956.6328125,
"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": 12.743997573852539,
"min": 0.38969916105270386,
"max": 12.785685539245605,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2485.07958984375,
"min": 75.60163879394531,
"max": 2608.27978515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06063799654236622,
"min": 0.06063799654236622,
"max": 0.07805219191450663,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24255198616946488,
"min": 0.24255198616946488,
"max": 0.39026095957253315,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2286877085765203,
"min": 0.13627377633169732,
"max": 0.2917814775424845,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9147508343060812,
"min": 0.5450951053267893,
"max": 1.4589073877124226,
"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": 24.795454545454547,
"min": 3.8863636363636362,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1091.0,
"min": 171.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.795454545454547,
"min": 3.8863636363636362,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1091.0,
"min": 171.0,
"max": 1376.0,
"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": "1763463932",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1763464304"
},
"total": 371.71531483499984,
"count": 1,
"self": 0.3212757809988034,
"children": {
"run_training.setup": {
"total": 0.024555601000429306,
"count": 1,
"self": 0.024555601000429306
},
"TrainerController.start_learning": {
"total": 371.3694834530006,
"count": 1,
"self": 0.3368126870236665,
"children": {
"TrainerController._reset_env": {
"total": 2.452700733000711,
"count": 1,
"self": 2.452700733000711
},
"TrainerController.advance": {
"total": 368.5018130959761,
"count": 18192,
"self": 0.34313209192714567,
"children": {
"env_step": {
"total": 256.28992146104247,
"count": 18192,
"self": 192.39693687315503,
"children": {
"SubprocessEnvManager._take_step": {
"total": 63.692425589960294,
"count": 18192,
"self": 1.1480366109262832,
"children": {
"TorchPolicy.evaluate": {
"total": 62.54438897903401,
"count": 18192,
"self": 62.54438897903401
}
}
},
"workers": {
"total": 0.20055899792714627,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 370.56173281395695,
"count": 18192,
"is_parallel": true,
"self": 200.85389782496623,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00206878599965421,
"count": 1,
"is_parallel": true,
"self": 0.0006632910008192994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014054949988349108,
"count": 10,
"is_parallel": true,
"self": 0.0014054949988349108
}
}
},
"UnityEnvironment.step": {
"total": 0.026428207000208204,
"count": 1,
"is_parallel": true,
"self": 0.0003947589993913425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002640270004121703,
"count": 1,
"is_parallel": true,
"self": 0.0002640270004121703
},
"communicator.exchange": {
"total": 0.02459641499990539,
"count": 1,
"is_parallel": true,
"self": 0.02459641499990539
},
"steps_from_proto": {
"total": 0.0011730060004992993,
"count": 1,
"is_parallel": true,
"self": 0.00026684199929150054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009061640012077987,
"count": 10,
"is_parallel": true,
"self": 0.0009061640012077987
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 169.70783498899073,
"count": 18191,
"is_parallel": true,
"self": 6.01482757098529,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.3593830560575952,
"count": 18191,
"is_parallel": true,
"self": 3.3593830560575952
},
"communicator.exchange": {
"total": 141.10677058995861,
"count": 18191,
"is_parallel": true,
"self": 141.10677058995861
},
"steps_from_proto": {
"total": 19.226853771989227,
"count": 18191,
"is_parallel": true,
"self": 3.641263842949229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.585589929039998,
"count": 181910,
"is_parallel": true,
"self": 15.585589929039998
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 111.86875954300649,
"count": 18192,
"self": 0.4148963451070813,
"children": {
"process_trajectory": {
"total": 24.39577450289562,
"count": 18192,
"self": 23.941235968894944,
"children": {
"RLTrainer._checkpoint": {
"total": 0.454538534000676,
"count": 4,
"self": 0.454538534000676
}
}
},
"_update_policy": {
"total": 87.05808869500379,
"count": 90,
"self": 35.339734068017606,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.718354626986184,
"count": 4587,
"self": 51.718354626986184
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1729998732334934e-06,
"count": 1,
"self": 1.1729998732334934e-06
},
"TrainerController._save_models": {
"total": 0.07815576400025748,
"count": 1,
"self": 0.0007046740001896978,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07745109000006778,
"count": 1,
"self": 0.07745109000006778
}
}
}
}
}
}
}