abdelhamidmalki's picture
First Push
d370040
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9431349039077759,
"min": 0.9431349039077759,
"max": 2.8665647506713867,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9025.80078125,
"min": 9025.80078125,
"max": 29451.0859375,
"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": 12.94825267791748,
"min": 0.40204185247421265,
"max": 12.981317520141602,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.9091796875,
"min": 77.9961166381836,
"max": 2637.465087890625,
"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": 0.0701830223026941,
"min": 0.0628490747419396,
"max": 0.07607837864905413,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2807320892107764,
"min": 0.2513962989677584,
"max": 0.3694942941462311,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20522219399172886,
"min": 0.1254616025470051,
"max": 0.2684333052705316,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8208887759669155,
"min": 0.5018464101880205,
"max": 1.3006340452269012,
"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": 25.386363636363637,
"min": 3.4545454545454546,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 152.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.4545454545454546,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 152.0,
"max": 1429.0,
"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": "1692464754",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692465407"
},
"total": 652.817770307,
"count": 1,
"self": 0.5920686300000852,
"children": {
"run_training.setup": {
"total": 0.055016032000025916,
"count": 1,
"self": 0.055016032000025916
},
"TrainerController.start_learning": {
"total": 652.1706856449999,
"count": 1,
"self": 0.9747453180085586,
"children": {
"TrainerController._reset_env": {
"total": 1.4328661480000164,
"count": 1,
"self": 1.4328661480000164
},
"TrainerController.advance": {
"total": 649.5976441239914,
"count": 18204,
"self": 0.46933003399055906,
"children": {
"env_step": {
"total": 649.1283140900008,
"count": 18204,
"self": 526.2155004889833,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.43488385301157,
"count": 18204,
"self": 3.322687963004114,
"children": {
"TorchPolicy.evaluate": {
"total": 119.11219589000746,
"count": 18204,
"self": 119.11219589000746
}
}
},
"workers": {
"total": 0.4779297480059199,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 649.5250910899969,
"count": 18204,
"is_parallel": true,
"self": 280.40529407499866,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0064484069999934945,
"count": 1,
"is_parallel": true,
"self": 0.004611366000062844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018370409999306503,
"count": 10,
"is_parallel": true,
"self": 0.0018370409999306503
}
}
},
"UnityEnvironment.step": {
"total": 0.04356204499998739,
"count": 1,
"is_parallel": true,
"self": 0.0007743030000142426,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003549399999656089,
"count": 1,
"is_parallel": true,
"self": 0.0003549399999656089
},
"communicator.exchange": {
"total": 0.0396855749999645,
"count": 1,
"is_parallel": true,
"self": 0.0396855749999645
},
"steps_from_proto": {
"total": 0.00274722700004304,
"count": 1,
"is_parallel": true,
"self": 0.0004976019998821357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002249625000160904,
"count": 10,
"is_parallel": true,
"self": 0.002249625000160904
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 369.1197970149982,
"count": 18203,
"is_parallel": true,
"self": 15.956545099998664,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.52578275099279,
"count": 18203,
"is_parallel": true,
"self": 8.52578275099279
},
"communicator.exchange": {
"total": 291.8940204820116,
"count": 18203,
"is_parallel": true,
"self": 291.8940204820116
},
"steps_from_proto": {
"total": 52.74344868199512,
"count": 18203,
"is_parallel": true,
"self": 10.499694798998632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 42.24375388299649,
"count": 182030,
"is_parallel": true,
"self": 42.24375388299649
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002016509999975824,
"count": 1,
"self": 0.0002016509999975824,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 643.8818240770064,
"count": 666462,
"is_parallel": true,
"self": 15.522333274014613,
"children": {
"process_trajectory": {
"total": 347.74711170299145,
"count": 666462,
"is_parallel": true,
"self": 345.97855094499147,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7685607579999783,
"count": 4,
"is_parallel": true,
"self": 1.7685607579999783
}
}
},
"_update_policy": {
"total": 280.61237910000034,
"count": 90,
"is_parallel": true,
"self": 105.82932001399797,
"children": {
"TorchPPOOptimizer.update": {
"total": 174.78305908600237,
"count": 4587,
"is_parallel": true,
"self": 174.78305908600237
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.16522840400000405,
"count": 1,
"self": 0.0012868470000739762,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16394155699993007,
"count": 1,
"self": 0.16394155699993007
}
}
}
}
}
}
}