nguyenduchuyiu's picture
First Push
c20c07a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.5044102668762207,
"min": 1.5044102668762207,
"max": 2.861304759979248,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 14430.3037109375,
"min": 14430.3037109375,
"max": 29428.51953125,
"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": 67.38893127441406,
"min": 0.441354900598526,
"max": 67.38893127441406,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 13140.841796875,
"min": 85.62284851074219,
"max": 13140.841796875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.09428895298273454,
"min": 0.09377022688328425,
"max": 0.1019628820663804,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.37715581193093817,
"min": 0.375080907533137,
"max": 0.5093329953303015,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.6821148916202433,
"min": 0.13913496408890436,
"max": 0.6821148916202433,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 2.728459566480973,
"min": 0.5565398563556174,
"max": 2.8631021503139946,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.694097306000002e-06,
"min": 2.694097306000002e-06,
"max": 9.729400270600001e-05,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0776389224000008e-05,
"min": 1.0776389224000008e-05,
"max": 0.00046172003828000015,
"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": 0.9617200000000001,
"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": 22.75,
"min": 3.909090909090909,
"max": 22.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1001.0,
"min": 172.0,
"max": 1250.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.75,
"min": 3.909090909090909,
"max": 22.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1001.0,
"min": 172.0,
"max": 1250.0,
"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": "1722700889",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 --resume --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722701527"
},
"total": 637.710038137,
"count": 1,
"self": 0.7550548739999385,
"children": {
"run_training.setup": {
"total": 0.05513231499992344,
"count": 1,
"self": 0.05513231499992344
},
"TrainerController.start_learning": {
"total": 636.8998509480001,
"count": 1,
"self": 0.5986415699987901,
"children": {
"TrainerController._reset_env": {
"total": 1.9320983549999937,
"count": 1,
"self": 1.9320983549999937
},
"TrainerController.advance": {
"total": 634.1369722430013,
"count": 18214,
"self": 0.2885012260169333,
"children": {
"env_step": {
"total": 633.8484710169844,
"count": 18214,
"self": 464.28821817698974,
"children": {
"SubprocessEnvManager._take_step": {
"total": 169.27154058999793,
"count": 18214,
"self": 1.5483321229977491,
"children": {
"TorchPolicy.evaluate": {
"total": 167.72320846700018,
"count": 18214,
"self": 167.72320846700018
}
}
},
"workers": {
"total": 0.2887122499967063,
"count": 18214,
"self": 0.0,
"children": {
"worker_root": {
"total": 635.3777962890165,
"count": 18214,
"is_parallel": true,
"self": 405.95797934301913,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002255387999980485,
"count": 1,
"is_parallel": true,
"self": 0.0006559520001019337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015994359998785512,
"count": 10,
"is_parallel": true,
"self": 0.0015994359998785512
}
}
},
"UnityEnvironment.step": {
"total": 0.03754347599999619,
"count": 1,
"is_parallel": true,
"self": 0.000653846999966845,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040510700000595534,
"count": 1,
"is_parallel": true,
"self": 0.00040510700000595534
},
"communicator.exchange": {
"total": 0.034366457000032824,
"count": 1,
"is_parallel": true,
"self": 0.034366457000032824
},
"steps_from_proto": {
"total": 0.0021180649999905654,
"count": 1,
"is_parallel": true,
"self": 0.0003892639999776293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017288010000129361,
"count": 10,
"is_parallel": true,
"self": 0.0017288010000129361
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.41981694599735,
"count": 18213,
"is_parallel": true,
"self": 10.339161144000286,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.403240264002193,
"count": 18213,
"is_parallel": true,
"self": 5.403240264002193
},
"communicator.exchange": {
"total": 178.62986377399602,
"count": 18213,
"is_parallel": true,
"self": 178.62986377399602
},
"steps_from_proto": {
"total": 35.047551763998854,
"count": 18213,
"is_parallel": true,
"self": 6.776084279946758,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.271467484052096,
"count": 182130,
"is_parallel": true,
"self": 28.271467484052096
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014187200008564105,
"count": 1,
"self": 0.00014187200008564105,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 628.9152889950208,
"count": 622823,
"is_parallel": true,
"self": 13.727376361968822,
"children": {
"process_trajectory": {
"total": 282.4212302110534,
"count": 622823,
"is_parallel": true,
"self": 280.8438673360538,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5773628749996078,
"count": 4,
"is_parallel": true,
"self": 1.5773628749996078
}
}
},
"_update_policy": {
"total": 332.76668242199855,
"count": 90,
"is_parallel": true,
"self": 83.28275330898941,
"children": {
"TorchPPOOptimizer.update": {
"total": 249.48392911300914,
"count": 15295,
"is_parallel": true,
"self": 249.48392911300914
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23199690799992823,
"count": 1,
"self": 0.002968395999914719,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2290285120000135,
"count": 1,
"self": 0.2290285120000135
}
}
}
}
}
}
}