rotemg8's picture
First Push
bb12ff1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9666321277618408,
"min": 0.9666321277618408,
"max": 2.865795850753784,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9229.4033203125,
"min": 9229.4033203125,
"max": 29348.615234375,
"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": 12.996901512145996,
"min": 0.3267396092414856,
"max": 12.996901512145996,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.395751953125,
"min": 63.387481689453125,
"max": 2633.515869140625,
"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": 0.06946407555084329,
"min": 0.0587741761791061,
"max": 0.07596914448989919,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27785630220337315,
"min": 0.2350967047164244,
"max": 0.379845722449496,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18980779418466137,
"min": 0.10559073669890709,
"max": 0.2955015319819544,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7592311767386455,
"min": 0.42236294679562836,
"max": 1.4775076599097718,
"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": 25.84090909090909,
"min": 3.1818181818181817,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 140.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.1818181818181817,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 140.0,
"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": "1709815446",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709815895"
},
"total": 448.6192736669999,
"count": 1,
"self": 0.7485307310000735,
"children": {
"run_training.setup": {
"total": 0.05466939799998727,
"count": 1,
"self": 0.05466939799998727
},
"TrainerController.start_learning": {
"total": 447.81607353799984,
"count": 1,
"self": 0.5804922209874803,
"children": {
"TrainerController._reset_env": {
"total": 2.910315646000072,
"count": 1,
"self": 2.910315646000072
},
"TrainerController.advance": {
"total": 444.1932552370123,
"count": 18206,
"self": 0.2907460290018662,
"children": {
"env_step": {
"total": 443.90250920801043,
"count": 18206,
"self": 288.74931110398495,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.868318686002,
"count": 18206,
"self": 1.4870199840103169,
"children": {
"TorchPolicy.evaluate": {
"total": 153.38129870199168,
"count": 18206,
"self": 153.38129870199168
}
}
},
"workers": {
"total": 0.28487941802347905,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.5835471889993,
"count": 18206,
"is_parallel": true,
"self": 219.8875764899933,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007990596000013284,
"count": 1,
"is_parallel": true,
"self": 0.00640901200006283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015815839999504533,
"count": 10,
"is_parallel": true,
"self": 0.0015815839999504533
}
}
},
"UnityEnvironment.step": {
"total": 0.03780523599994012,
"count": 1,
"is_parallel": true,
"self": 0.0007247629999937999,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042966000000888016,
"count": 1,
"is_parallel": true,
"self": 0.00042966000000888016
},
"communicator.exchange": {
"total": 0.034692473999939466,
"count": 1,
"is_parallel": true,
"self": 0.034692473999939466
},
"steps_from_proto": {
"total": 0.0019583389999979772,
"count": 1,
"is_parallel": true,
"self": 0.00039791199992578186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015604270000721954,
"count": 10,
"is_parallel": true,
"self": 0.0015604270000721954
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.695970699006,
"count": 18205,
"is_parallel": true,
"self": 10.45676367500539,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.352391515991144,
"count": 18205,
"is_parallel": true,
"self": 5.352391515991144
},
"communicator.exchange": {
"total": 176.88257615599093,
"count": 18205,
"is_parallel": true,
"self": 176.88257615599093
},
"steps_from_proto": {
"total": 34.004239352018544,
"count": 18205,
"is_parallel": true,
"self": 6.457628501032218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.546610850986326,
"count": 182050,
"is_parallel": true,
"self": 27.546610850986326
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010586300004433724,
"count": 1,
"self": 0.00010586300004433724,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.6935985529907,
"count": 673651,
"is_parallel": true,
"self": 14.608489405046384,
"children": {
"process_trajectory": {
"total": 242.43997178294535,
"count": 673651,
"is_parallel": true,
"self": 241.4542871319453,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9856846510000423,
"count": 4,
"is_parallel": true,
"self": 0.9856846510000423
}
}
},
"_update_policy": {
"total": 181.64513736499896,
"count": 90,
"is_parallel": true,
"self": 52.09706570499657,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.5480716600024,
"count": 4587,
"is_parallel": true,
"self": 129.5480716600024
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13190457099995,
"count": 1,
"self": 0.0013256479999199655,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13057892300003004,
"count": 1,
"self": 0.13057892300003004
}
}
}
}
}
}
}