mirikle's picture
First Push
ee6664c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7248789668083191,
"min": 0.7081558704376221,
"max": 2.8580827713012695,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6889.24951171875,
"min": 6889.24951171875,
"max": 29175.30859375,
"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": 13.064432144165039,
"min": 0.5138588547706604,
"max": 13.064432144165039,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2547.564208984375,
"min": 99.68861389160156,
"max": 2663.282958984375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06434934316961981,
"min": 0.06144909066924632,
"max": 0.07468702239281153,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25739737267847923,
"min": 0.2457963626769853,
"max": 0.36021633924033,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19541350270018856,
"min": 0.1540614491324032,
"max": 0.30656432515265897,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7816540108007543,
"min": 0.6162457965296128,
"max": 1.5328216257632947,
"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": 25.318181818181817,
"min": 3.9545454545454546,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 174.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.9545454545454546,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 174.0,
"max": 1423.0,
"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": "1742668495",
"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": "1742668992"
},
"total": 497.09945894999987,
"count": 1,
"self": 0.4885345119997737,
"children": {
"run_training.setup": {
"total": 0.0323191960000031,
"count": 1,
"self": 0.0323191960000031
},
"TrainerController.start_learning": {
"total": 496.5786052420001,
"count": 1,
"self": 0.443309430000113,
"children": {
"TrainerController._reset_env": {
"total": 3.2987355550000075,
"count": 1,
"self": 3.2987355550000075
},
"TrainerController.advance": {
"total": 492.7205225319999,
"count": 18192,
"self": 0.4617600600112155,
"children": {
"env_step": {
"total": 355.7624011119909,
"count": 18192,
"self": 270.21679211099,
"children": {
"SubprocessEnvManager._take_step": {
"total": 85.27417720899041,
"count": 18192,
"self": 1.483075174987107,
"children": {
"TorchPolicy.evaluate": {
"total": 83.7911020340033,
"count": 18192,
"self": 83.7911020340033
}
}
},
"workers": {
"total": 0.27143179201050316,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 494.88944931500214,
"count": 18192,
"is_parallel": true,
"self": 258.1800242320187,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005899018000036449,
"count": 1,
"is_parallel": true,
"self": 0.003965337999829899,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019336800002065502,
"count": 10,
"is_parallel": true,
"self": 0.0019336800002065502
}
}
},
"UnityEnvironment.step": {
"total": 0.04247574200007875,
"count": 1,
"is_parallel": true,
"self": 0.0006388809999862133,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004376250000177606,
"count": 1,
"is_parallel": true,
"self": 0.0004376250000177606
},
"communicator.exchange": {
"total": 0.03931719600007,
"count": 1,
"is_parallel": true,
"self": 0.03931719600007
},
"steps_from_proto": {
"total": 0.002082040000004781,
"count": 1,
"is_parallel": true,
"self": 0.0003884449998849959,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016935950001197853,
"count": 10,
"is_parallel": true,
"self": 0.0016935950001197853
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.70942508298344,
"count": 18191,
"is_parallel": true,
"self": 11.229199078967099,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.4164396180251515,
"count": 18191,
"is_parallel": true,
"self": 6.4164396180251515
},
"communicator.exchange": {
"total": 181.44918494400906,
"count": 18191,
"is_parallel": true,
"self": 181.44918494400906
},
"steps_from_proto": {
"total": 37.61460144198213,
"count": 18191,
"is_parallel": true,
"self": 6.921267654021676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.693333787960455,
"count": 181910,
"is_parallel": true,
"self": 30.693333787960455
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 136.49636135999776,
"count": 18192,
"self": 0.5828270149931996,
"children": {
"process_trajectory": {
"total": 30.720559758004697,
"count": 18192,
"self": 30.168721839004434,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5518379190002634,
"count": 4,
"self": 0.5518379190002634
}
}
},
"_update_policy": {
"total": 105.19297458699987,
"count": 90,
"self": 42.439693008004156,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.75328157899571,
"count": 4587,
"self": 62.75328157899571
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.630000477045542e-07,
"count": 1,
"self": 9.630000477045542e-07
},
"TrainerController._save_models": {
"total": 0.11603676200002155,
"count": 1,
"self": 0.0011915820000467647,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11484517999997479,
"count": 1,
"self": 0.11484517999997479
}
}
}
}
}
}
}