rusuanjun's picture
First Push
35fa523 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8525007963180542,
"min": 0.8356553316116333,
"max": 2.815582752227783,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8102.16748046875,
"min": 8102.16748046875,
"max": 28741.46875,
"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": 13.166397094726562,
"min": 0.3618370592594147,
"max": 13.166397094726562,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2567.447509765625,
"min": 70.1963882446289,
"max": 2670.867431640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06311127301374012,
"min": 0.06311127301374012,
"max": 0.07453521460696469,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25244509205496046,
"min": 0.25244509205496046,
"max": 0.3726760730348235,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19650566946788162,
"min": 0.1336276267641498,
"max": 0.33003343466450186,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7860226778715265,
"min": 0.5345105070565992,
"max": 1.529301631392217,
"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": 26.204545454545453,
"min": 3.8863636363636362,
"max": 26.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1153.0,
"min": 171.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.204545454545453,
"min": 3.8863636363636362,
"max": 26.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1153.0,
"min": 171.0,
"max": 1422.0,
"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": "1746549027",
"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": "1746549456"
},
"total": 429.3975148300001,
"count": 1,
"self": 0.43052218700017875,
"children": {
"run_training.setup": {
"total": 0.03694026599998779,
"count": 1,
"self": 0.03694026599998779
},
"TrainerController.start_learning": {
"total": 428.9300523769999,
"count": 1,
"self": 0.3454831099969624,
"children": {
"TrainerController._reset_env": {
"total": 3.690277335000019,
"count": 1,
"self": 3.690277335000019
},
"TrainerController.advance": {
"total": 424.811622561003,
"count": 18192,
"self": 0.3806267789999538,
"children": {
"env_step": {
"total": 300.29289248100656,
"count": 18192,
"self": 230.32332617800728,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.76616257399962,
"count": 18192,
"self": 1.265071355990358,
"children": {
"TorchPolicy.evaluate": {
"total": 68.50109121800926,
"count": 18192,
"self": 68.50109121800926
}
}
},
"workers": {
"total": 0.20340372899966042,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.5447055960009,
"count": 18192,
"is_parallel": true,
"self": 225.62342702299168,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00612811899998178,
"count": 1,
"is_parallel": true,
"self": 0.004591904999642793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015362140003389868,
"count": 10,
"is_parallel": true,
"self": 0.0015362140003389868
}
}
},
"UnityEnvironment.step": {
"total": 0.03916400799994335,
"count": 1,
"is_parallel": true,
"self": 0.0005676370000173847,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004589010000017879,
"count": 1,
"is_parallel": true,
"self": 0.0004589010000017879
},
"communicator.exchange": {
"total": 0.036298188999921877,
"count": 1,
"is_parallel": true,
"self": 0.036298188999921877
},
"steps_from_proto": {
"total": 0.0018392810000023019,
"count": 1,
"is_parallel": true,
"self": 0.00036405200012268324,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014752289998796186,
"count": 10,
"is_parallel": true,
"self": 0.0014752289998796186
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 201.9212785730092,
"count": 18191,
"is_parallel": true,
"self": 9.839545421997741,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.4837970020034845,
"count": 18191,
"is_parallel": true,
"self": 5.4837970020034845
},
"communicator.exchange": {
"total": 155.1698918240072,
"count": 18191,
"is_parallel": true,
"self": 155.1698918240072
},
"steps_from_proto": {
"total": 31.42804432500077,
"count": 18191,
"is_parallel": true,
"self": 5.702100582011099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.72594374298967,
"count": 181910,
"is_parallel": true,
"self": 25.72594374298967
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.13810330099648,
"count": 18192,
"self": 0.44071573899736904,
"children": {
"process_trajectory": {
"total": 27.1106912279987,
"count": 18192,
"self": 26.706099468998787,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4045917589999135,
"count": 4,
"self": 0.4045917589999135
}
}
},
"_update_policy": {
"total": 96.58669633400041,
"count": 90,
"self": 39.97141925799019,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.615277076010216,
"count": 4587,
"self": 56.615277076010216
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.450000106880907e-07,
"count": 1,
"self": 9.450000106880907e-07
},
"TrainerController._save_models": {
"total": 0.08266842599994106,
"count": 1,
"self": 0.0010449219998918124,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08162350400004925,
"count": 1,
"self": 0.08162350400004925
}
}
}
}
}
}
}