akter-sust's picture
First Snowball
8598161
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9699063897132874,
"min": 0.9699063897132874,
"max": 2.8640050888061523,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9260.666015625,
"min": 9260.666015625,
"max": 29330.275390625,
"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": 12.424060821533203,
"min": 0.3994687795639038,
"max": 12.45712947845459,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2422.69189453125,
"min": 77.49694061279297,
"max": 2541.25439453125,
"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": 0.07091848161058699,
"min": 0.06259161429839236,
"max": 0.07599623518934309,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28367392644234796,
"min": 0.2503664571935694,
"max": 0.3664798565110758,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19911540390960142,
"min": 0.11810066618821949,
"max": 0.2928668567362954,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7964616156384057,
"min": 0.47240266475287795,
"max": 1.3629950118415495,
"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": 24.136363636363637,
"min": 3.340909090909091,
"max": 24.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1062.0,
"min": 147.0,
"max": 1347.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.136363636363637,
"min": 3.340909090909091,
"max": 24.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1062.0,
"min": 147.0,
"max": 1347.0,
"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": "1698645633",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698646085"
},
"total": 452.33601519800004,
"count": 1,
"self": 0.4261362010000198,
"children": {
"run_training.setup": {
"total": 0.04879880400000047,
"count": 1,
"self": 0.04879880400000047
},
"TrainerController.start_learning": {
"total": 451.861080193,
"count": 1,
"self": 0.5194922570043445,
"children": {
"TrainerController._reset_env": {
"total": 8.704321712000024,
"count": 1,
"self": 8.704321712000024
},
"TrainerController.advance": {
"total": 442.5467088069955,
"count": 18199,
"self": 0.2382458959930318,
"children": {
"env_step": {
"total": 442.3084629110025,
"count": 18199,
"self": 300.78068320000693,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.26932353299685,
"count": 18199,
"self": 1.3653674519979404,
"children": {
"TorchPolicy.evaluate": {
"total": 139.9039560809989,
"count": 18199,
"self": 139.9039560809989
}
}
},
"workers": {
"total": 0.2584561779987098,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 450.66004839300535,
"count": 18199,
"is_parallel": true,
"self": 222.2698842850101,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006087347999994108,
"count": 1,
"is_parallel": true,
"self": 0.00465290499994353,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014344430000505781,
"count": 10,
"is_parallel": true,
"self": 0.0014344430000505781
}
}
},
"UnityEnvironment.step": {
"total": 0.037016584999946645,
"count": 1,
"is_parallel": true,
"self": 0.0006485919999477119,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003729869999915536,
"count": 1,
"is_parallel": true,
"self": 0.0003729869999915536
},
"communicator.exchange": {
"total": 0.034078125000064574,
"count": 1,
"is_parallel": true,
"self": 0.034078125000064574
},
"steps_from_proto": {
"total": 0.001916880999942805,
"count": 1,
"is_parallel": true,
"self": 0.00040363200002957456,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015132489999132304,
"count": 10,
"is_parallel": true,
"self": 0.0015132489999132304
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.39016410799525,
"count": 18198,
"is_parallel": true,
"self": 10.222981796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.200365204005038,
"count": 18198,
"is_parallel": true,
"self": 5.200365204005038
},
"communicator.exchange": {
"total": 180.70958624499144,
"count": 18198,
"is_parallel": true,
"self": 180.70958624499144
},
"steps_from_proto": {
"total": 32.25723086299877,
"count": 18198,
"is_parallel": true,
"self": 5.767818265010192,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.489412597988576,
"count": 181980,
"is_parallel": true,
"self": 26.489412597988576
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015901200004009297,
"count": 1,
"self": 0.00015901200004009297,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.87106263297346,
"count": 471586,
"is_parallel": true,
"self": 9.886407821993998,
"children": {
"process_trajectory": {
"total": 249.08778359497978,
"count": 471586,
"is_parallel": true,
"self": 248.24175252097984,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8460310739999386,
"count": 4,
"is_parallel": true,
"self": 0.8460310739999386
}
}
},
"_update_policy": {
"total": 179.89687121599968,
"count": 90,
"is_parallel": true,
"self": 54.904346563998274,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.9925246520014,
"count": 4587,
"is_parallel": true,
"self": 124.9925246520014
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09039840500008722,
"count": 1,
"self": 0.001106573000129174,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08929183199995805,
"count": 1,
"self": 0.08929183199995805
}
}
}
}
}
}
}