SwordAndTea's picture
First Push
1d69673 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9566828012466431,
"min": 0.9566828012466431,
"max": 2.8553123474121094,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9144.9306640625,
"min": 9144.9306640625,
"max": 29304.0703125,
"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": 12.579802513122559,
"min": 0.31582748889923096,
"max": 12.579802513122559,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2453.0615234375,
"min": 61.27053451538086,
"max": 2544.8623046875,
"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": 0.07129415231497213,
"min": 0.06055382485575654,
"max": 0.07508128970021419,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2851766092598885,
"min": 0.24221529942302616,
"max": 0.37299306022578094,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20997127182051248,
"min": 0.13684498985736246,
"max": 0.2614418168278302,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8398850872820499,
"min": 0.5473799594294498,
"max": 1.3072090841391508,
"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": 25.0,
"min": 3.9545454545454546,
"max": 25.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 174.0,
"max": 1370.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.9545454545454546,
"max": 25.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 174.0,
"max": 1370.0,
"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": "1729129389",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729129985"
},
"total": 596.382783334,
"count": 1,
"self": 0.8625528710000481,
"children": {
"run_training.setup": {
"total": 0.06556105499998921,
"count": 1,
"self": 0.06556105499998921
},
"TrainerController.start_learning": {
"total": 595.454669408,
"count": 1,
"self": 0.8684199270006729,
"children": {
"TrainerController._reset_env": {
"total": 5.719857740000066,
"count": 1,
"self": 5.719857740000066
},
"TrainerController.advance": {
"total": 588.7435171619991,
"count": 18205,
"self": 0.4064284790036936,
"children": {
"env_step": {
"total": 588.3370886829954,
"count": 18205,
"self": 452.6935544460058,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.22506299899476,
"count": 18205,
"self": 2.227077010001949,
"children": {
"TorchPolicy.evaluate": {
"total": 132.9979859889928,
"count": 18205,
"self": 132.9979859889928
}
}
},
"workers": {
"total": 0.41847123799482233,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 593.4235128689937,
"count": 18205,
"is_parallel": true,
"self": 278.59578032199477,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024491320000379346,
"count": 1,
"is_parallel": true,
"self": 0.0007494790002056106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001699652999832324,
"count": 10,
"is_parallel": true,
"self": 0.001699652999832324
}
}
},
"UnityEnvironment.step": {
"total": 0.10916079699995862,
"count": 1,
"is_parallel": true,
"self": 0.0010114119999116156,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004297130000168181,
"count": 1,
"is_parallel": true,
"self": 0.0004297130000168181
},
"communicator.exchange": {
"total": 0.10492349700007253,
"count": 1,
"is_parallel": true,
"self": 0.10492349700007253
},
"steps_from_proto": {
"total": 0.002796174999957657,
"count": 1,
"is_parallel": true,
"self": 0.0005549740000105885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022412009999470683,
"count": 10,
"is_parallel": true,
"self": 0.0022412009999470683
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 314.82773254699896,
"count": 18204,
"is_parallel": true,
"self": 14.627516496994758,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.4061020480004345,
"count": 18204,
"is_parallel": true,
"self": 7.4061020480004345
},
"communicator.exchange": {
"total": 249.46885183099891,
"count": 18204,
"is_parallel": true,
"self": 249.46885183099891
},
"steps_from_proto": {
"total": 43.32526217100485,
"count": 18204,
"is_parallel": true,
"self": 8.433996747985361,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.89126542301949,
"count": 182040,
"is_parallel": true,
"self": 34.89126542301949
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019539100003385101,
"count": 1,
"self": 0.00019539100003385101,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 581.8624293229509,
"count": 777197,
"is_parallel": true,
"self": 17.399090386953503,
"children": {
"process_trajectory": {
"total": 313.97336763199723,
"count": 777197,
"is_parallel": true,
"self": 313.0973910639973,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8759765679999418,
"count": 4,
"is_parallel": true,
"self": 0.8759765679999418
}
}
},
"_update_policy": {
"total": 250.48997130400016,
"count": 90,
"is_parallel": true,
"self": 71.0088288060058,
"children": {
"TorchPPOOptimizer.update": {
"total": 179.48114249799437,
"count": 4587,
"is_parallel": true,
"self": 179.48114249799437
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12267918800012012,
"count": 1,
"self": 0.002069778000077349,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12060941000004277,
"count": 1,
"self": 0.12060941000004277
}
}
}
}
}
}
}