haith1307's picture
First Push
43ce918 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.931429922580719,
"min": 0.931429922580719,
"max": 2.8677191734313965,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8893.29296875,
"min": 8893.29296875,
"max": 29368.3125,
"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": 12.687347412109375,
"min": 0.39921754598617554,
"max": 12.749470710754395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2474.03271484375,
"min": 77.44820404052734,
"max": 2600.89208984375,
"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": 0.06854895715286166,
"min": 0.06466574861340132,
"max": 0.07431255928160822,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27419582861144665,
"min": 0.2586629944536053,
"max": 0.37156279640804113,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.187387476803041,
"min": 0.12516118419315556,
"max": 0.28810556472516524,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.749549907212164,
"min": 0.5006447367726222,
"max": 1.4405278236258263,
"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": 24.931818181818183,
"min": 3.522727272727273,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 155.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.522727272727273,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 155.0,
"max": 1398.0,
"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": "1712217624",
"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": "1712218114"
},
"total": 490.46428541,
"count": 1,
"self": 0.44278331300006357,
"children": {
"run_training.setup": {
"total": 0.05521741999996266,
"count": 1,
"self": 0.05521741999996266
},
"TrainerController.start_learning": {
"total": 489.966284677,
"count": 1,
"self": 0.665860570003133,
"children": {
"TrainerController._reset_env": {
"total": 2.799725952000017,
"count": 1,
"self": 2.799725952000017
},
"TrainerController.advance": {
"total": 486.40495625199674,
"count": 18199,
"self": 0.3311778199879427,
"children": {
"env_step": {
"total": 486.0737784320088,
"count": 18199,
"self": 316.47045616299783,
"children": {
"SubprocessEnvManager._take_step": {
"total": 169.26137124200977,
"count": 18199,
"self": 1.6402829669834773,
"children": {
"TorchPolicy.evaluate": {
"total": 167.6210882750263,
"count": 18199,
"self": 167.6210882750263
}
}
},
"workers": {
"total": 0.34195102700118696,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 488.5772534740074,
"count": 18199,
"is_parallel": true,
"self": 243.0396782790292,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007380118999890328,
"count": 1,
"is_parallel": true,
"self": 0.005607925000276737,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017721939996135916,
"count": 10,
"is_parallel": true,
"self": 0.0017721939996135916
}
}
},
"UnityEnvironment.step": {
"total": 0.038332039000124496,
"count": 1,
"is_parallel": true,
"self": 0.0007169969999267778,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042591000010361313,
"count": 1,
"is_parallel": true,
"self": 0.00042591000010361313
},
"communicator.exchange": {
"total": 0.03498972300008063,
"count": 1,
"is_parallel": true,
"self": 0.03498972300008063
},
"steps_from_proto": {
"total": 0.0021994090000134747,
"count": 1,
"is_parallel": true,
"self": 0.0004211850000501727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001778223999963302,
"count": 10,
"is_parallel": true,
"self": 0.001778223999963302
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.53757519497822,
"count": 18198,
"is_parallel": true,
"self": 11.182078686983004,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.0004448489862625,
"count": 18198,
"is_parallel": true,
"self": 6.0004448489862625
},
"communicator.exchange": {
"total": 190.86926592100122,
"count": 18198,
"is_parallel": true,
"self": 190.86926592100122
},
"steps_from_proto": {
"total": 37.485785738007735,
"count": 18198,
"is_parallel": true,
"self": 7.327101030981794,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.15868470702594,
"count": 181980,
"is_parallel": true,
"self": 30.15868470702594
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001405190000696166,
"count": 1,
"self": 0.0001405190000696166,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 480.27207612204893,
"count": 734195,
"is_parallel": true,
"self": 15.910732486024017,
"children": {
"process_trajectory": {
"total": 266.18262001402513,
"count": 734195,
"is_parallel": true,
"self": 265.3530515350251,
"children": {
"RLTrainer._checkpoint": {
"total": 0.829568479000045,
"count": 4,
"is_parallel": true,
"self": 0.829568479000045
}
}
},
"_update_policy": {
"total": 198.17872362199978,
"count": 90,
"is_parallel": true,
"self": 55.42497237099906,
"children": {
"TorchPPOOptimizer.update": {
"total": 142.75375125100072,
"count": 4587,
"is_parallel": true,
"self": 142.75375125100072
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0956013840000196,
"count": 1,
"self": 0.000989388000107283,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09461199599991232,
"count": 1,
"self": 0.09461199599991232
}
}
}
}
}
}
}