kostasang's picture
First push
d7e5e37
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9199188351631165,
"min": 0.9199188351631165,
"max": 2.864410400390625,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8793.50390625,
"min": 8793.50390625,
"max": 29334.42578125,
"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": 13.068626403808594,
"min": 0.5300133228302002,
"max": 13.068626403808594,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.382080078125,
"min": 102.82258605957031,
"max": 2645.32861328125,
"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": 0.07260631820513391,
"min": 0.06250951233061428,
"max": 0.07318185643674166,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29042527282053565,
"min": 0.2500380493224571,
"max": 0.34806402725813557,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2138757754628565,
"min": 0.13573826833025496,
"max": 0.27205533015669564,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.855503101851426,
"min": 0.5429530733210198,
"max": 1.353166558286723,
"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": 25.431818181818183,
"min": 3.7954545454545454,
"max": 26.163636363636364,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 167.0,
"max": 1439.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 3.7954545454545454,
"max": 26.163636363636364,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 167.0,
"max": 1439.0,
"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": "1674552718",
"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": "1674553148"
},
"total": 430.07256103200007,
"count": 1,
"self": 0.3932224310001402,
"children": {
"run_training.setup": {
"total": 0.10360075300002336,
"count": 1,
"self": 0.10360075300002336
},
"TrainerController.start_learning": {
"total": 429.5757378479999,
"count": 1,
"self": 0.5884512580024648,
"children": {
"TrainerController._reset_env": {
"total": 10.265521895999996,
"count": 1,
"self": 10.265521895999996
},
"TrainerController.advance": {
"total": 418.6094548859977,
"count": 18203,
"self": 0.2808191459895397,
"children": {
"env_step": {
"total": 418.32863574000817,
"count": 18203,
"self": 276.69198271502626,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.3591816219904,
"count": 18203,
"self": 1.3832805539803985,
"children": {
"TorchPolicy.evaluate": {
"total": 139.97590106801,
"count": 18203,
"self": 31.427579001004688,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.5483220670053,
"count": 18203,
"self": 108.5483220670053
}
}
}
}
},
"workers": {
"total": 0.27747140299152306,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 428.3091259000147,
"count": 18203,
"is_parallel": true,
"self": 203.99441231100866,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.012336840999978449,
"count": 1,
"is_parallel": true,
"self": 0.004971355999941807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.007365485000036642,
"count": 10,
"is_parallel": true,
"self": 0.007365485000036642
}
}
},
"UnityEnvironment.step": {
"total": 0.04998457499993947,
"count": 1,
"is_parallel": true,
"self": 0.0005146229999581919,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030498099999931583,
"count": 1,
"is_parallel": true,
"self": 0.00030498099999931583
},
"communicator.exchange": {
"total": 0.047397857999953885,
"count": 1,
"is_parallel": true,
"self": 0.047397857999953885
},
"steps_from_proto": {
"total": 0.0017671130000280755,
"count": 1,
"is_parallel": true,
"self": 0.0004141610000942819,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013529519999337936,
"count": 10,
"is_parallel": true,
"self": 0.0013529519999337936
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.31471358900603,
"count": 18202,
"is_parallel": true,
"self": 8.385986571984063,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.834100102008847,
"count": 18202,
"is_parallel": true,
"self": 4.834100102008847
},
"communicator.exchange": {
"total": 179.07728735699902,
"count": 18202,
"is_parallel": true,
"self": 179.07728735699902
},
"steps_from_proto": {
"total": 32.0173395580141,
"count": 18202,
"is_parallel": true,
"self": 6.601163500998268,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.416176057015832,
"count": 182020,
"is_parallel": true,
"self": 25.416176057015832
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.941999989365286e-05,
"count": 1,
"self": 3.941999989365286e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 415.9572288490575,
"count": 343727,
"is_parallel": true,
"self": 8.8343827120475,
"children": {
"process_trajectory": {
"total": 239.08196004300987,
"count": 343727,
"is_parallel": true,
"self": 238.30114423300984,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7808158100000355,
"count": 4,
"is_parallel": true,
"self": 0.7808158100000355
}
}
},
"_update_policy": {
"total": 168.04088609400014,
"count": 90,
"is_parallel": true,
"self": 42.90240424399701,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.13848185000313,
"count": 4587,
"is_parallel": true,
"self": 125.13848185000313
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11227038799984257,
"count": 1,
"self": 0.0007963289999679546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11147405899987461,
"count": 1,
"self": 0.11147405899987461
}
}
}
}
}
}
}