PhoenixA's picture
First Push
e7e8cf2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8097304701805115,
"min": 0.7872291207313538,
"max": 2.870267629623413,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7695.67822265625,
"min": 7695.67822265625,
"max": 29299.69140625,
"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": 13.155234336853027,
"min": 0.2573680579662323,
"max": 13.155234336853027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.270751953125,
"min": 49.929405212402344,
"max": 2659.173828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.067140648025516,
"min": 0.06464111750794795,
"max": 0.07424012584019424,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.268562592102064,
"min": 0.26507450110283587,
"max": 0.3712006292009712,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1808674397567908,
"min": 0.11411457478214859,
"max": 0.27701521409200686,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7234697590271632,
"min": 0.45645829912859437,
"max": 1.3806568293594847,
"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": 25.75,
"min": 2.8181818181818183,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 124.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 2.8181818181818183,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 124.0,
"max": 1426.0,
"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": "1769120795",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/root/miniconda3/envs/mlagents_env/bin/mlagents-learn /content/ml-agents/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769121217"
},
"total": 421.47747971099943,
"count": 1,
"self": 0.4882576539985166,
"children": {
"run_training.setup": {
"total": 0.022113722000540292,
"count": 1,
"self": 0.022113722000540292
},
"TrainerController.start_learning": {
"total": 420.9671083350004,
"count": 1,
"self": 0.3280805339336439,
"children": {
"TrainerController._reset_env": {
"total": 3.691486290999819,
"count": 1,
"self": 3.691486290999819
},
"TrainerController.advance": {
"total": 416.8714655650665,
"count": 18192,
"self": 0.35609495092467114,
"children": {
"env_step": {
"total": 301.25229377509186,
"count": 18192,
"self": 235.55252444108282,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.49981725499583,
"count": 18192,
"self": 1.2028542818998176,
"children": {
"TorchPolicy.evaluate": {
"total": 64.29696297309602,
"count": 18192,
"self": 64.29696297309602
}
}
},
"workers": {
"total": 0.199952079013201,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.04692802104273,
"count": 18192,
"is_parallel": true,
"self": 212.1602055760468,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052141819996904815,
"count": 1,
"is_parallel": true,
"self": 0.0031428729998879135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002071308999802568,
"count": 10,
"is_parallel": true,
"self": 0.002071308999802568
}
}
},
"UnityEnvironment.step": {
"total": 0.04299725700002455,
"count": 1,
"is_parallel": true,
"self": 0.0005495870009326609,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003769229997487855,
"count": 1,
"is_parallel": true,
"self": 0.0003769229997487855
},
"communicator.exchange": {
"total": 0.03833300299993425,
"count": 1,
"is_parallel": true,
"self": 0.03833300299993425
},
"steps_from_proto": {
"total": 0.003737743999408849,
"count": 1,
"is_parallel": true,
"self": 0.00035645999832922826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003381284001079621,
"count": 10,
"is_parallel": true,
"self": 0.003381284001079621
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.88672244499594,
"count": 18191,
"is_parallel": true,
"self": 9.993606214898136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.259033276961418,
"count": 18191,
"is_parallel": true,
"self": 5.259033276961418
},
"communicator.exchange": {
"total": 157.23228884108175,
"count": 18191,
"is_parallel": true,
"self": 157.23228884108175
},
"steps_from_proto": {
"total": 34.40179411205463,
"count": 18191,
"is_parallel": true,
"self": 6.384776790937394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.017017321117237,
"count": 181910,
"is_parallel": true,
"self": 28.017017321117237
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 115.26307683904997,
"count": 18192,
"self": 0.3960428390664674,
"children": {
"process_trajectory": {
"total": 25.201815066981,
"count": 18192,
"self": 24.76408987098148,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4377251959995192,
"count": 4,
"self": 0.4377251959995192
}
}
},
"_update_policy": {
"total": 89.6652189330025,
"count": 90,
"self": 36.996402846982164,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.66881608602034,
"count": 4587,
"self": 52.66881608602034
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.332000465481542e-06,
"count": 1,
"self": 1.332000465481542e-06
},
"TrainerController._save_models": {
"total": 0.07607461299994611,
"count": 1,
"self": 0.0006885849998070626,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07538602800013905,
"count": 1,
"self": 0.07538602800013905
}
}
}
}
}
}
}