hsinyen5's picture
First Push
f1f6077 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8454803824424744,
"min": 0.8391631245613098,
"max": 2.840406894683838,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8035.4453125,
"min": 8035.4453125,
"max": 28994.873046875,
"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": 11.20400619506836,
"min": 0.4274580776691437,
"max": 11.20400619506836,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2184.78125,
"min": 82.92686462402344,
"max": 2256.116455078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06900181822814322,
"min": 0.062154016576481376,
"max": 0.07374481218650152,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2760072729125729,
"min": 0.2486160663059255,
"max": 0.36807932565102863,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17561365437566065,
"min": 0.13944146197458146,
"max": 0.27847307452968517,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7024546175026426,
"min": 0.5577658478983258,
"max": 1.392365372648426,
"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": 22.15909090909091,
"min": 4.318181818181818,
"max": 22.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 975.0,
"min": 190.0,
"max": 1200.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.15909090909091,
"min": 4.318181818181818,
"max": 22.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 975.0,
"min": 190.0,
"max": 1200.0,
"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": "1747983385",
"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": "1747983812"
},
"total": 427.793254877,
"count": 1,
"self": 0.7609806829998433,
"children": {
"run_training.setup": {
"total": 0.022799864000035086,
"count": 1,
"self": 0.022799864000035086
},
"TrainerController.start_learning": {
"total": 427.0094743300001,
"count": 1,
"self": 0.3285303519910485,
"children": {
"TrainerController._reset_env": {
"total": 3.857633203999967,
"count": 1,
"self": 3.857633203999967
},
"TrainerController.advance": {
"total": 422.6925156480095,
"count": 18192,
"self": 0.3547260640348213,
"children": {
"env_step": {
"total": 297.8078995420012,
"count": 18192,
"self": 227.44584091603474,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.16964326296397,
"count": 18192,
"self": 1.217533489936386,
"children": {
"TorchPolicy.evaluate": {
"total": 68.95210977302759,
"count": 18192,
"self": 68.95210977302759
}
}
},
"workers": {
"total": 0.19241536300251028,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.61508734101176,
"count": 18192,
"is_parallel": true,
"self": 225.96741085204985,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005063329999984489,
"count": 1,
"is_parallel": true,
"self": 0.003621591000182889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014417389998016006,
"count": 10,
"is_parallel": true,
"self": 0.0014417389998016006
}
}
},
"UnityEnvironment.step": {
"total": 0.06529778399999486,
"count": 1,
"is_parallel": true,
"self": 0.0005569429999923159,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003785759997754212,
"count": 1,
"is_parallel": true,
"self": 0.0003785759997754212
},
"communicator.exchange": {
"total": 0.06268703700015976,
"count": 1,
"is_parallel": true,
"self": 0.06268703700015976
},
"steps_from_proto": {
"total": 0.0016752280000673636,
"count": 1,
"is_parallel": true,
"self": 0.0003049299994017929,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013702980006655707,
"count": 10,
"is_parallel": true,
"self": 0.0013702980006655707
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 199.6476764889619,
"count": 18191,
"is_parallel": true,
"self": 9.85066668890272,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.408790782006918,
"count": 18191,
"is_parallel": true,
"self": 5.408790782006918
},
"communicator.exchange": {
"total": 153.78606036100905,
"count": 18191,
"is_parallel": true,
"self": 153.78606036100905
},
"steps_from_proto": {
"total": 30.60215865704322,
"count": 18191,
"is_parallel": true,
"self": 5.460127127970054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.142031529073165,
"count": 181910,
"is_parallel": true,
"self": 25.142031529073165
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.52989004197343,
"count": 18192,
"self": 0.39717472498318784,
"children": {
"process_trajectory": {
"total": 27.515756734992465,
"count": 18192,
"self": 27.067143266992616,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4486134679998486,
"count": 4,
"self": 0.4486134679998486
}
}
},
"_update_policy": {
"total": 96.61695858199778,
"count": 90,
"self": 39.70819911697981,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.908759465017965,
"count": 4587,
"self": 56.908759465017965
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1279998943791725e-06,
"count": 1,
"self": 1.1279998943791725e-06
},
"TrainerController._save_models": {
"total": 0.13079399799971725,
"count": 1,
"self": 0.0011401349997868238,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12965386299993042,
"count": 1,
"self": 0.12965386299993042
}
}
}
}
}
}
}