maxhykw's picture
First Push
de5ec0b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.4676002264022827,
"min": 1.4676002264022827,
"max": 2.865382432937622,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 15110.412109375,
"min": 14615.3974609375,
"max": 29249.82421875,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.851430892944336,
"min": 0.3180241584777832,
"max": 8.851430892944336,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1805.69189453125,
"min": 61.696685791015625,
"max": 1805.69189453125,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06643667409958902,
"min": 0.06188728170792612,
"max": 0.07164904480669065,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3321833704979451,
"min": 0.2475491268317045,
"max": 0.35528739949679183,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2435227394104004,
"min": 0.12072056710866153,
"max": 0.27108295429863183,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.217613697052002,
"min": 0.4828822684346461,
"max": 1.3012448148984535,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 18.854545454545455,
"min": 3.2954545454545454,
"max": 18.854545454545455,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1037.0,
"min": 145.0,
"max": 1037.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 18.854545454545455,
"min": 3.2954545454545454,
"max": 18.854545454545455,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1037.0,
"min": 145.0,
"max": 1037.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1741999107",
"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": "1741999321"
},
"total": 214.13856211000007,
"count": 1,
"self": 0.4604680780000763,
"children": {
"run_training.setup": {
"total": 0.029300249000016265,
"count": 1,
"self": 0.029300249000016265
},
"TrainerController.start_learning": {
"total": 213.64879378299997,
"count": 1,
"self": 0.16998397598990778,
"children": {
"TrainerController._reset_env": {
"total": 3.2476423749999412,
"count": 1,
"self": 3.2476423749999412
},
"TrainerController.advance": {
"total": 210.12700474401026,
"count": 9128,
"self": 0.18071891401405082,
"children": {
"env_step": {
"total": 148.87581159200545,
"count": 9128,
"self": 112.98757754599592,
"children": {
"SubprocessEnvManager._take_step": {
"total": 35.78591140800654,
"count": 9128,
"self": 0.6296297190085625,
"children": {
"TorchPolicy.evaluate": {
"total": 35.15628168899798,
"count": 9128,
"self": 35.15628168899798
}
}
},
"workers": {
"total": 0.10232263800298824,
"count": 9128,
"self": 0.0,
"children": {
"worker_root": {
"total": 212.80529190599282,
"count": 9128,
"is_parallel": true,
"self": 113.9096907179669,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007931739000014204,
"count": 1,
"is_parallel": true,
"self": 0.004123755000136953,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0038079839998772513,
"count": 10,
"is_parallel": true,
"self": 0.0038079839998772513
}
}
},
"UnityEnvironment.step": {
"total": 0.034365155999921626,
"count": 1,
"is_parallel": true,
"self": 0.000587275000043519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003931940000256873,
"count": 1,
"is_parallel": true,
"self": 0.0003931940000256873
},
"communicator.exchange": {
"total": 0.03140603099996042,
"count": 1,
"is_parallel": true,
"self": 0.03140603099996042
},
"steps_from_proto": {
"total": 0.0019786559998919984,
"count": 1,
"is_parallel": true,
"self": 0.0003690099997584184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00160964600013358,
"count": 10,
"is_parallel": true,
"self": 0.00160964600013358
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 98.89560118802592,
"count": 9127,
"is_parallel": true,
"self": 4.869269370039092,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.7254505429868914,
"count": 9127,
"is_parallel": true,
"self": 2.7254505429868914
},
"communicator.exchange": {
"total": 75.40943473300308,
"count": 9127,
"is_parallel": true,
"self": 75.40943473300308
},
"steps_from_proto": {
"total": 15.891446541996856,
"count": 9127,
"is_parallel": true,
"self": 2.8329403019927213,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.058506240004135,
"count": 91270,
"is_parallel": true,
"self": 13.058506240004135
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 61.070474237990766,
"count": 9128,
"self": 0.20979872399129817,
"children": {
"process_trajectory": {
"total": 13.641742682999848,
"count": 9128,
"self": 13.387851203000082,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2538914799997656,
"count": 2,
"self": 0.2538914799997656
}
}
},
"_update_policy": {
"total": 47.21893283099962,
"count": 45,
"self": 19.091847849002306,
"children": {
"TorchPPOOptimizer.update": {
"total": 28.127084981997314,
"count": 2292,
"self": 28.127084981997314
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0859998837986495e-06,
"count": 1,
"self": 1.0859998837986495e-06
},
"TrainerController._save_models": {
"total": 0.10416160199997648,
"count": 1,
"self": 0.0009921639998538012,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10316943800012268,
"count": 1,
"self": 0.10316943800012268
}
}
}
}
}
}
}