codeSpaghetti's picture
First Push
3bec821
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8894709944725037,
"min": 0.8894709944725037,
"max": 2.8670074939727783,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8512.2373046875,
"min": 8512.2373046875,
"max": 29424.09765625,
"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": 12.991353988647461,
"min": 0.19915089011192322,
"max": 12.991353988647461,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2533.31396484375,
"min": 38.63527297973633,
"max": 2616.0927734375,
"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": 0.06071165546988293,
"min": 0.06071165546988293,
"max": 0.07806767017338608,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2428466218795317,
"min": 0.2428466218795317,
"max": 0.3560955717415103,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21087516113823535,
"min": 0.10792926523615332,
"max": 0.2947215908298305,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8435006445529414,
"min": 0.43171706094461326,
"max": 1.396560046602698,
"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": 25.318181818181817,
"min": 2.9318181818181817,
"max": 25.8,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 129.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 2.9318181818181817,
"max": 25.8,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 129.0,
"max": 1419.0,
"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": "1679236729",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679237181"
},
"total": 451.704669471,
"count": 1,
"self": 0.43039420999997446,
"children": {
"run_training.setup": {
"total": 0.12766808700001775,
"count": 1,
"self": 0.12766808700001775
},
"TrainerController.start_learning": {
"total": 451.146607174,
"count": 1,
"self": 0.5605209259935009,
"children": {
"TrainerController._reset_env": {
"total": 9.26782391399999,
"count": 1,
"self": 9.26782391399999
},
"TrainerController.advance": {
"total": 441.1929027740065,
"count": 18204,
"self": 0.2771972930018478,
"children": {
"env_step": {
"total": 440.91570548100464,
"count": 18204,
"self": 320.41558818701554,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.23895300899571,
"count": 18204,
"self": 2.4142919699921492,
"children": {
"TorchPolicy.evaluate": {
"total": 117.82466103900356,
"count": 18204,
"self": 117.82466103900356
}
}
},
"workers": {
"total": 0.2611642849933844,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.84892055600363,
"count": 18204,
"is_parallel": true,
"self": 215.86683069000134,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005069300000002386,
"count": 1,
"is_parallel": true,
"self": 0.0035561769999503667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001513123000052019,
"count": 10,
"is_parallel": true,
"self": 0.001513123000052019
}
}
},
"UnityEnvironment.step": {
"total": 0.03430460100000232,
"count": 1,
"is_parallel": true,
"self": 0.0005794000000207689,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033541400000558497,
"count": 1,
"is_parallel": true,
"self": 0.00033541400000558497
},
"communicator.exchange": {
"total": 0.03161164299999086,
"count": 1,
"is_parallel": true,
"self": 0.03161164299999086
},
"steps_from_proto": {
"total": 0.0017781439999851045,
"count": 1,
"is_parallel": true,
"self": 0.0003731259999995018,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014050179999856027,
"count": 10,
"is_parallel": true,
"self": 0.0014050179999856027
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.9820898660023,
"count": 18203,
"is_parallel": true,
"self": 9.221672421004712,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.064100480999372,
"count": 18203,
"is_parallel": true,
"self": 5.064100480999372
},
"communicator.exchange": {
"total": 189.7388347189976,
"count": 18203,
"is_parallel": true,
"self": 189.7388347189976
},
"steps_from_proto": {
"total": 29.95748224500062,
"count": 18203,
"is_parallel": true,
"self": 5.881473776990646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.076008468009974,
"count": 182030,
"is_parallel": true,
"self": 24.076008468009974
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.62980000420066e-05,
"count": 1,
"self": 8.62980000420066e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 437.98635253401676,
"count": 388216,
"is_parallel": true,
"self": 9.411983475023305,
"children": {
"process_trajectory": {
"total": 240.6475134239934,
"count": 388216,
"is_parallel": true,
"self": 239.87555035499346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7719630689999235,
"count": 4,
"is_parallel": true,
"self": 0.7719630689999235
}
}
},
"_update_policy": {
"total": 187.92685563500007,
"count": 90,
"is_parallel": true,
"self": 69.86723768100055,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.05961795399952,
"count": 4587,
"is_parallel": true,
"self": 118.05961795399952
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1252732619999506,
"count": 1,
"self": 0.0008508609998898464,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12442240100006074,
"count": 1,
"self": 0.12442240100006074
}
}
}
}
}
}
}