QuantumInstability's picture
First Push
a2cdbfc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9751336574554443,
"min": 0.9751336574554443,
"max": 2.8636765480041504,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9310.576171875,
"min": 9310.576171875,
"max": 29326.912109375,
"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": 11.912372589111328,
"min": 0.30103281140327454,
"max": 11.912372589111328,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2322.91259765625,
"min": 58.400367736816406,
"max": 2404.76953125,
"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.Losses.PolicyLoss.mean": {
"value": 0.07103267186846328,
"min": 0.062453951832253995,
"max": 0.07523543045010905,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2841306874738531,
"min": 0.25342741014045556,
"max": 0.3748311080020286,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20062076220033218,
"min": 0.11190131880621444,
"max": 0.2904919617316302,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8024830488013287,
"min": 0.44760527522485777,
"max": 1.452459808658151,
"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.CumulativeReward.mean": {
"value": 23.75,
"min": 2.9545454545454546,
"max": 23.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1045.0,
"min": 130.0,
"max": 1292.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.75,
"min": 2.9545454545454546,
"max": 23.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1045.0,
"min": 130.0,
"max": 1292.0,
"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": "1713271452",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713271921"
},
"total": 469.6459408439996,
"count": 1,
"self": 0.4458528289997048,
"children": {
"run_training.setup": {
"total": 0.059892983000281674,
"count": 1,
"self": 0.059892983000281674
},
"TrainerController.start_learning": {
"total": 469.1401950319996,
"count": 1,
"self": 0.6092154419861799,
"children": {
"TrainerController._reset_env": {
"total": 3.020692349000001,
"count": 1,
"self": 3.020692349000001
},
"TrainerController.advance": {
"total": 465.41863422901315,
"count": 18198,
"self": 0.3199046440267921,
"children": {
"env_step": {
"total": 465.09872958498636,
"count": 18198,
"self": 302.03985398893883,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.74480345603433,
"count": 18198,
"self": 1.5615426190470316,
"children": {
"TorchPolicy.evaluate": {
"total": 161.1832608369873,
"count": 18198,
"self": 161.1832608369873
}
}
},
"workers": {
"total": 0.31407214001319517,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 467.88735925403626,
"count": 18198,
"is_parallel": true,
"self": 233.94754929799547,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008789214999978867,
"count": 1,
"is_parallel": true,
"self": 0.007298662999346561,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014905520006323059,
"count": 10,
"is_parallel": true,
"self": 0.0014905520006323059
}
}
},
"UnityEnvironment.step": {
"total": 0.04187789599973257,
"count": 1,
"is_parallel": true,
"self": 0.0007406229997286573,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000515486000040255,
"count": 1,
"is_parallel": true,
"self": 0.000515486000040255
},
"communicator.exchange": {
"total": 0.03847375799978181,
"count": 1,
"is_parallel": true,
"self": 0.03847375799978181
},
"steps_from_proto": {
"total": 0.0021480290001818503,
"count": 1,
"is_parallel": true,
"self": 0.0004289409998818883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001719088000299962,
"count": 10,
"is_parallel": true,
"self": 0.001719088000299962
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.9398099560408,
"count": 18197,
"is_parallel": true,
"self": 10.696712581041538,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.631112432032296,
"count": 18197,
"is_parallel": true,
"self": 5.631112432032296
},
"communicator.exchange": {
"total": 183.45166770396418,
"count": 18197,
"is_parallel": true,
"self": 183.45166770396418
},
"steps_from_proto": {
"total": 34.16031723900278,
"count": 18197,
"is_parallel": true,
"self": 6.510315043900391,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.650002195102388,
"count": 181970,
"is_parallel": true,
"self": 27.650002195102388
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012792500001523877,
"count": 1,
"self": 0.00012792500001523877,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.8587904977853,
"count": 685722,
"is_parallel": true,
"self": 14.371483999138945,
"children": {
"process_trajectory": {
"total": 255.2915475656455,
"count": 685722,
"is_parallel": true,
"self": 254.47343632464526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8181112410002243,
"count": 4,
"is_parallel": true,
"self": 0.8181112410002243
}
}
},
"_update_policy": {
"total": 190.1957589330009,
"count": 90,
"is_parallel": true,
"self": 52.90487936799582,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.29087956500507,
"count": 4587,
"is_parallel": true,
"self": 137.29087956500507
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09152508700026374,
"count": 1,
"self": 0.0010632319999785977,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09046185500028514,
"count": 1,
"self": 0.09046185500028514
}
}
}
}
}
}
}