RamonAnkersmit's picture
Eerste Push
e3c59df
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5323686599731445,
"min": 0.5315052270889282,
"max": 2.8783111572265625,
"count": 250
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5469.5556640625,
"min": 5080.9658203125,
"max": 29476.78515625,
"count": 250
},
"SnowballTarget.Step.mean": {
"value": 2499968.0,
"min": 9952.0,
"max": 2499968.0,
"count": 250
},
"SnowballTarget.Step.sum": {
"value": 2499968.0,
"min": 9952.0,
"max": 2499968.0,
"count": 250
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.28403091430664,
"min": 0.24573512375354767,
"max": 14.378103256225586,
"count": 250
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2913.9423828125,
"min": 47.67261505126953,
"max": 2947.51123046875,
"count": 250
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 250
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 250
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.066692001996579,
"min": 0.06280100351924536,
"max": 0.07545941886450985,
"count": 250
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.333460009982895,
"min": 0.25120401407698145,
"max": 0.37729709432254926,
"count": 250
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15302406994735493,
"min": 0.11267911145627937,
"max": 0.2754589585346334,
"count": 250
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7651203497367747,
"min": 0.4507164458251175,
"max": 1.3772947926731671,
"count": 250
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.116197884799984e-07,
"min": 2.116197884799984e-07,
"max": 9.978352021648003e-05,
"count": 250
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0580989423999919e-06,
"min": 1.0580989423999919e-06,
"max": 0.0004969376030624,
"count": 250
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10021152,
"min": 0.10021152,
"max": 0.19978352,
"count": 250
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5010576,
"min": 0.4024300799999999,
"max": 0.9969376000000001,
"count": 250
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.055484799999992e-05,
"min": 2.055484799999992e-05,
"max": 0.004989197648000001,
"count": 250
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001027742399999996,
"min": 0.0001027742399999996,
"max": 0.02484718624,
"count": 250
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.29090909090909,
"min": 3.0,
"max": 28.545454545454547,
"count": 250
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1556.0,
"min": 132.0,
"max": 1558.0,
"count": 250
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.29090909090909,
"min": 3.0,
"max": 28.545454545454547,
"count": 250
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1556.0,
"min": 132.0,
"max": 1558.0,
"count": 250
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 250
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 250
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674846391",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674851973"
},
"total": 5582.3295853849995,
"count": 1,
"self": 0.4375020809993657,
"children": {
"run_training.setup": {
"total": 0.09893708899994635,
"count": 1,
"self": 0.09893708899994635
},
"TrainerController.start_learning": {
"total": 5581.793146215,
"count": 1,
"self": 6.018418668052618,
"children": {
"TrainerController._reset_env": {
"total": 8.952535562000094,
"count": 1,
"self": 8.952535562000094
},
"TrainerController.advance": {
"total": 5566.707200790947,
"count": 227334,
"self": 3.1657263681472614,
"children": {
"env_step": {
"total": 5563.5414744228,
"count": 227334,
"self": 3839.1867349277486,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1721.2958190470329,
"count": 227334,
"self": 16.842551399896593,
"children": {
"TorchPolicy.evaluate": {
"total": 1704.4532676471363,
"count": 227334,
"self": 378.97872296096875,
"children": {
"TorchPolicy.sample_actions": {
"total": 1325.4745446861675,
"count": 227334,
"self": 1325.4745446861675
}
}
}
}
},
"workers": {
"total": 3.0589204480185117,
"count": 227334,
"self": 0.0,
"children": {
"worker_root": {
"total": 5567.941482871953,
"count": 227334,
"is_parallel": true,
"self": 2960.704601914156,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00525408199996491,
"count": 1,
"is_parallel": true,
"self": 0.0033256140000048617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019284679999600485,
"count": 10,
"is_parallel": true,
"self": 0.0019284679999600485
}
}
},
"UnityEnvironment.step": {
"total": 0.0332679640000606,
"count": 1,
"is_parallel": true,
"self": 0.0006062939999083028,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026996400004009047,
"count": 1,
"is_parallel": true,
"self": 0.00026996400004009047
},
"communicator.exchange": {
"total": 0.03062492900005509,
"count": 1,
"is_parallel": true,
"self": 0.03062492900005509
},
"steps_from_proto": {
"total": 0.0017667770000571181,
"count": 1,
"is_parallel": true,
"self": 0.00041202299985343416,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001354754000203684,
"count": 10,
"is_parallel": true,
"self": 0.001354754000203684
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2607.236880957797,
"count": 227333,
"is_parallel": true,
"self": 99.6438305098086,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 57.51582607204273,
"count": 227333,
"is_parallel": true,
"self": 57.51582607204273
},
"communicator.exchange": {
"total": 2099.130631281879,
"count": 227333,
"is_parallel": true,
"self": 2099.130631281879
},
"steps_from_proto": {
"total": 350.946593094067,
"count": 227333,
"is_parallel": true,
"self": 74.11644845618866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 276.83014463787833,
"count": 2273330,
"is_parallel": true,
"self": 276.83014463787833
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.013499983557267e-05,
"count": 1,
"self": 4.013499983557267e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 5532.115867223496,
"count": 4092475,
"is_parallel": true,
"self": 103.3297026453074,
"children": {
"process_trajectory": {
"total": 2808.6560995311916,
"count": 4092475,
"is_parallel": true,
"self": 2807.798040593192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8580589379994308,
"count": 5,
"is_parallel": true,
"self": 0.8580589379994308
}
}
},
"_update_policy": {
"total": 2620.1300650469975,
"count": 1136,
"is_parallel": true,
"self": 823.4347584171151,
"children": {
"TorchPPOOptimizer.update": {
"total": 1796.6953066298825,
"count": 96555,
"is_parallel": true,
"self": 1796.6953066298825
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11495105900030467,
"count": 1,
"self": 0.0009146940010396065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11403636499926506,
"count": 1,
"self": 0.11403636499926506
}
}
}
}
}
}
}