amihk's picture
First Push
9abfb91 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8353955149650574,
"min": 0.8353955149650574,
"max": 2.8659350872039795,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7939.59912109375,
"min": 7939.59912109375,
"max": 29255.46484375,
"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": 13.124088287353516,
"min": 0.46752145886421204,
"max": 13.124088287353516,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2559.197265625,
"min": 90.69916534423828,
"max": 2674.0556640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07516693794077225,
"min": 0.06325460929382483,
"max": 0.07691393329585872,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.300667751763089,
"min": 0.267610614154917,
"max": 0.37347195940246286,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19509169583519298,
"min": 0.12350139145365022,
"max": 0.29674913244796736,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7803667833407719,
"min": 0.49400556581460087,
"max": 1.4196480240891962,
"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": 25.863636363636363,
"min": 3.5454545454545454,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 156.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.5454545454545454,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 156.0,
"max": 1429.0,
"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": "1761022615",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1761023190"
},
"total": 575.53961044,
"count": 1,
"self": 0.5932841290000397,
"children": {
"run_training.setup": {
"total": 0.042384856000012405,
"count": 1,
"self": 0.042384856000012405
},
"TrainerController.start_learning": {
"total": 574.903941455,
"count": 1,
"self": 0.6106686170012381,
"children": {
"TrainerController._reset_env": {
"total": 3.5144925110000145,
"count": 1,
"self": 3.5144925110000145
},
"TrainerController.advance": {
"total": 570.7011342479988,
"count": 18192,
"self": 0.6751683960073933,
"children": {
"env_step": {
"total": 411.8355156769973,
"count": 18192,
"self": 357.6811618650073,
"children": {
"SubprocessEnvManager._take_step": {
"total": 53.78001844599345,
"count": 18192,
"self": 1.997040863989639,
"children": {
"TorchPolicy.evaluate": {
"total": 51.78297758200381,
"count": 18192,
"self": 51.78297758200381
}
}
},
"workers": {
"total": 0.3743353659965578,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 571.9084978640066,
"count": 18192,
"is_parallel": true,
"self": 262.78469562700326,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006188243999986298,
"count": 1,
"is_parallel": true,
"self": 0.003791403999969134,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002396840000017164,
"count": 10,
"is_parallel": true,
"self": 0.002396840000017164
}
}
},
"UnityEnvironment.step": {
"total": 0.04176972499999465,
"count": 1,
"is_parallel": true,
"self": 0.0007209940000052484,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004620530000352119,
"count": 1,
"is_parallel": true,
"self": 0.0004620530000352119
},
"communicator.exchange": {
"total": 0.03816016299998637,
"count": 1,
"is_parallel": true,
"self": 0.03816016299998637
},
"steps_from_proto": {
"total": 0.0024265149999678215,
"count": 1,
"is_parallel": true,
"self": 0.0004330080000158887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001993506999951933,
"count": 10,
"is_parallel": true,
"self": 0.001993506999951933
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 309.1238022370033,
"count": 18191,
"is_parallel": true,
"self": 14.404098239001485,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.441075482000713,
"count": 18191,
"is_parallel": true,
"self": 7.441075482000713
},
"communicator.exchange": {
"total": 238.42589151400904,
"count": 18191,
"is_parallel": true,
"self": 238.42589151400904
},
"steps_from_proto": {
"total": 48.85273700199207,
"count": 18191,
"is_parallel": true,
"self": 8.82951286300056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.02322413899151,
"count": 181910,
"is_parallel": true,
"self": 40.02322413899151
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 158.19045017499406,
"count": 18192,
"self": 0.7998479510033576,
"children": {
"process_trajectory": {
"total": 30.497309548990586,
"count": 18192,
"self": 29.94256460499065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5547449439999355,
"count": 4,
"self": 0.5547449439999355
}
}
},
"_update_policy": {
"total": 126.89329267500011,
"count": 90,
"self": 48.637387447005835,
"children": {
"TorchPPOOptimizer.update": {
"total": 78.25590522799428,
"count": 4587,
"self": 78.25590522799428
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3970000054541742e-06,
"count": 1,
"self": 1.3970000054541742e-06
},
"TrainerController._save_models": {
"total": 0.07764468200002739,
"count": 1,
"self": 0.0009755959999893093,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07666908600003808,
"count": 1,
"self": 0.07666908600003808
}
}
}
}
}
}
}