mjishu's picture
First Push
7b2b087 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6868813633918762,
"min": 0.6868813633918762,
"max": 2.869704484939575,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6528.12060546875,
"min": 6528.12060546875,
"max": 29293.943359375,
"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": 13.1204252243042,
"min": 0.44000887870788574,
"max": 13.1204252243042,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2558.48291015625,
"min": 85.36172485351562,
"max": 2663.5615234375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06906412124578541,
"min": 0.06252268948204195,
"max": 0.07453559668247893,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27625648498314165,
"min": 0.2500907579281678,
"max": 0.3628406231517004,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18459950719832205,
"min": 0.11231809982792565,
"max": 0.28837106204500385,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7383980287932882,
"min": 0.4492723993117026,
"max": 1.4418553102250191,
"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": 26.068181818181817,
"min": 3.2954545454545454,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1147.0,
"min": 145.0,
"max": 1420.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.068181818181817,
"min": 3.2954545454545454,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1147.0,
"min": 145.0,
"max": 1420.0,
"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": "1739292416",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739292830"
},
"total": 414.384829068,
"count": 1,
"self": 0.43791989199996806,
"children": {
"run_training.setup": {
"total": 0.022774615000002996,
"count": 1,
"self": 0.022774615000002996
},
"TrainerController.start_learning": {
"total": 413.924134561,
"count": 1,
"self": 0.30277568899964535,
"children": {
"TrainerController._reset_env": {
"total": 3.263448595,
"count": 1,
"self": 3.263448595
},
"TrainerController.advance": {
"total": 410.2745315730004,
"count": 18192,
"self": 0.3348626589902324,
"children": {
"env_step": {
"total": 288.76727548400163,
"count": 18192,
"self": 219.3504991310033,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.22742819399997,
"count": 18192,
"self": 1.199197982001067,
"children": {
"TorchPolicy.evaluate": {
"total": 68.0282302119989,
"count": 18192,
"self": 68.0282302119989
}
}
},
"workers": {
"total": 0.18934815899837076,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.4845900869967,
"count": 18192,
"is_parallel": true,
"self": 219.88162540899629,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005731580000031045,
"count": 1,
"is_parallel": true,
"self": 0.00357839100001911,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021531890000119347,
"count": 10,
"is_parallel": true,
"self": 0.0021531890000119347
}
}
},
"UnityEnvironment.step": {
"total": 0.056538647000024866,
"count": 1,
"is_parallel": true,
"self": 0.0005491480000614501,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003708090000031916,
"count": 1,
"is_parallel": true,
"self": 0.0003708090000031916
},
"communicator.exchange": {
"total": 0.05397507999998652,
"count": 1,
"is_parallel": true,
"self": 0.05397507999998652
},
"steps_from_proto": {
"total": 0.0016436099999737053,
"count": 1,
"is_parallel": true,
"self": 0.0003127780000227176,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013308319999509877,
"count": 10,
"is_parallel": true,
"self": 0.0013308319999509877
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.60296467800043,
"count": 18191,
"is_parallel": true,
"self": 9.400003919989445,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.297848152000768,
"count": 18191,
"is_parallel": true,
"self": 5.297848152000768
},
"communicator.exchange": {
"total": 147.85104864201168,
"count": 18191,
"is_parallel": true,
"self": 147.85104864201168
},
"steps_from_proto": {
"total": 30.054063963998544,
"count": 18191,
"is_parallel": true,
"self": 5.205429133983785,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.84863483001476,
"count": 181910,
"is_parallel": true,
"self": 24.84863483001476
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.17239343000853,
"count": 18192,
"self": 0.3679508940057872,
"children": {
"process_trajectory": {
"total": 26.60142051900209,
"count": 18192,
"self": 25.996036598002092,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6053839209999978,
"count": 4,
"self": 0.6053839209999978
}
}
},
"_update_policy": {
"total": 94.20302201700065,
"count": 90,
"self": 37.608540810000875,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.594481206999774,
"count": 4587,
"self": 56.594481206999774
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.660000159783522e-07,
"count": 1,
"self": 9.660000159783522e-07
},
"TrainerController._save_models": {
"total": 0.0833777379999674,
"count": 1,
"self": 0.0008824099999173995,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08249532800005,
"count": 1,
"self": 0.08249532800005
}
}
}
}
}
}
}