Weiming1122's picture
First Push
c21121d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.839410126209259,
"min": 0.839410126209259,
"max": 2.844252109527588,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 42363.3515625,
"min": 40732.9296875,
"max": 144451.03125,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 52536.0,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 1999800.0,
"min": 49800.0,
"max": 1999800.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 1999800.0,
"min": 49800.0,
"max": 1999800.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.501752853393555,
"min": 0.5022461414337158,
"max": 14.501752853393555,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 3625.438232421875,
"min": 125.05929565429688,
"max": 3625.438232421875,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.388,
"min": 5.008032128514056,
"max": 28.448,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 7097.0,
"min": 1247.0,
"max": 7112.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.388,
"min": 5.008032128514056,
"max": 28.448,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 7097.0,
"min": 1247.0,
"max": 7112.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.069219311003226,
"min": 0.0659932713580287,
"max": 0.0739939942222383,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.276877244012904,
"min": 0.2639730854321148,
"max": 0.3581072422068817,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15687800026407428,
"min": 0.14771346322836815,
"max": 0.2919780290740378,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6275120010562971,
"min": 0.6275120010562971,
"max": 1.3910198542445091,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.825098724999995e-06,
"min": 3.825098724999995e-06,
"max": 0.00029587500137499996,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.530039489999998e-05,
"min": 1.530039489999998e-05,
"max": 0.0014422500192499998,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10127499999999999,
"min": 0.10127499999999999,
"max": 0.19862500000000005,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40509999999999996,
"min": 0.40509999999999996,
"max": 0.9807500000000001,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.362249999999992e-05,
"min": 7.362249999999992e-05,
"max": 0.0049313875,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002944899999999997,
"min": 0.0002944899999999997,
"max": 0.024039425,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703744704",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703749228"
},
"total": 4524.0049186979995,
"count": 1,
"self": 0.6768422829991323,
"children": {
"run_training.setup": {
"total": 0.06769795000002432,
"count": 1,
"self": 0.06769795000002432
},
"TrainerController.start_learning": {
"total": 4523.260378465,
"count": 1,
"self": 6.153770934033673,
"children": {
"TrainerController._reset_env": {
"total": 3.387389077000023,
"count": 1,
"self": 3.387389077000023
},
"TrainerController.advance": {
"total": 4513.5815245649665,
"count": 182002,
"self": 2.794995134952842,
"children": {
"env_step": {
"total": 4510.786529430014,
"count": 182002,
"self": 2907.504590901017,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1600.249445852959,
"count": 182002,
"self": 15.010505520020615,
"children": {
"TorchPolicy.evaluate": {
"total": 1585.2389403329385,
"count": 182002,
"self": 1585.2389403329385
}
}
},
"workers": {
"total": 3.032492676037407,
"count": 182002,
"self": 0.0,
"children": {
"worker_root": {
"total": 4511.344607695967,
"count": 182002,
"is_parallel": true,
"self": 2199.071089124015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004833086000019193,
"count": 1,
"is_parallel": true,
"self": 0.003405404999966777,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014276810000524165,
"count": 10,
"is_parallel": true,
"self": 0.0014276810000524165
}
}
},
"UnityEnvironment.step": {
"total": 0.0377329269999791,
"count": 1,
"is_parallel": true,
"self": 0.0007396139999968909,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040095899998959794,
"count": 1,
"is_parallel": true,
"self": 0.00040095899998959794
},
"communicator.exchange": {
"total": 0.034467437999978756,
"count": 1,
"is_parallel": true,
"self": 0.034467437999978756
},
"steps_from_proto": {
"total": 0.0021249160000138545,
"count": 1,
"is_parallel": true,
"self": 0.00041478200006395127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017101339999499032,
"count": 10,
"is_parallel": true,
"self": 0.0017101339999499032
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2312.273518571952,
"count": 182001,
"is_parallel": true,
"self": 110.96179828893128,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 53.66522611495839,
"count": 182001,
"is_parallel": true,
"self": 53.66522611495839
},
"communicator.exchange": {
"total": 1805.0553392249547,
"count": 182001,
"is_parallel": true,
"self": 1805.0553392249547
},
"steps_from_proto": {
"total": 342.5911549431076,
"count": 182001,
"is_parallel": true,
"self": 63.7990347122423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 278.7921202308653,
"count": 1820010,
"is_parallel": true,
"self": 278.7921202308653
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.001607125000191445,
"count": 1,
"self": 0.001607125000191445,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 4457.231079032006,
"count": 6689180,
"is_parallel": true,
"self": 142.82890651324124,
"children": {
"process_trajectory": {
"total": 2243.318894835765,
"count": 6689180,
"is_parallel": true,
"self": 2242.5206855647652,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7982092709999051,
"count": 4,
"is_parallel": true,
"self": 0.7982092709999051
}
}
},
"_update_policy": {
"total": 2071.0832776830002,
"count": 181,
"is_parallel": true,
"self": 620.9278815499742,
"children": {
"TorchPPOOptimizer.update": {
"total": 1450.155396133026,
"count": 46161,
"is_parallel": true,
"self": 1450.155396133026
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1360867639996286,
"count": 1,
"self": 0.0017097370000556111,
"children": {
"RLTrainer._checkpoint": {
"total": 0.134377026999573,
"count": 1,
"self": 0.134377026999573
}
}
}
}
}
}
}