albraa3adil's picture
First Push
8c80cf3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.748667299747467,
"min": 0.725486159324646,
"max": 2.8257362842559814,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7181.216796875,
"min": 6911.6240234375,
"max": 28845.115234375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 27.390087127685547,
"min": 0.5206656455993652,
"max": 27.395498275756836,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 5614.9677734375,
"min": 101.0091323852539,
"max": 5614.9677734375,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06385836195507127,
"min": 0.060768997639716674,
"max": 0.07670492233626325,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.31929180977535637,
"min": 0.25327973217673727,
"max": 0.38352461168131624,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20600742224384758,
"min": 0.1329871159202109,
"max": 0.3407507467211462,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.030037111219238,
"min": 0.5319484636808436,
"max": 1.6844288925914204,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.849378982400002e-06,
"min": 2.849378982400002e-06,
"max": 0.0002769692810824,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.424689491200001e-05,
"min": 1.424689491200001e-05,
"max": 0.0013571264153120002,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.2,
"min": 3.1818181818181817,
"max": 27.386363636363637,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1441.0,
"min": 140.0,
"max": 1475.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.2,
"min": 3.1818181818181817,
"max": 27.386363636363637,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1441.0,
"min": 140.0,
"max": 1475.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1770068005",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1770069017"
},
"total": 1012.8412620929998,
"count": 1,
"self": 0.7499912729999778,
"children": {
"run_training.setup": {
"total": 0.02517740099983712,
"count": 1,
"self": 0.02517740099983712
},
"TrainerController.start_learning": {
"total": 1012.066093419,
"count": 1,
"self": 0.7348823230167909,
"children": {
"TrainerController._reset_env": {
"total": 2.989187002000108,
"count": 1,
"self": 2.989187002000108
},
"TrainerController.advance": {
"total": 1008.2665412569831,
"count": 45464,
"self": 0.811443711947959,
"children": {
"env_step": {
"total": 723.8095192590235,
"count": 45464,
"self": 563.9526610720759,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.38900039397868,
"count": 45464,
"self": 2.9405123489173093,
"children": {
"TorchPolicy.evaluate": {
"total": 156.44848804506137,
"count": 45464,
"self": 156.44848804506137
}
}
},
"workers": {
"total": 0.4678577929689709,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1007.609892953958,
"count": 45464,
"is_parallel": true,
"self": 511.1881915050121,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004845215999921493,
"count": 1,
"is_parallel": true,
"self": 0.0034663990008994006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013788169990220922,
"count": 10,
"is_parallel": true,
"self": 0.0013788169990220922
}
}
},
"UnityEnvironment.step": {
"total": 0.05628643500040198,
"count": 1,
"is_parallel": true,
"self": 0.0006054440004845674,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041473000010228134,
"count": 1,
"is_parallel": true,
"self": 0.00041473000010228134
},
"communicator.exchange": {
"total": 0.05136292899987893,
"count": 1,
"is_parallel": true,
"self": 0.05136292899987893
},
"steps_from_proto": {
"total": 0.0039033319999361993,
"count": 1,
"is_parallel": true,
"self": 0.000381498000024294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0035218339999119053,
"count": 10,
"is_parallel": true,
"self": 0.0035218339999119053
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 496.4217014489459,
"count": 45463,
"is_parallel": true,
"self": 24.560102531898792,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.720871838959283,
"count": 45463,
"is_parallel": true,
"self": 12.720871838959283
},
"communicator.exchange": {
"total": 375.84355196505476,
"count": 45463,
"is_parallel": true,
"self": 375.84355196505476
},
"steps_from_proto": {
"total": 83.29717511303306,
"count": 45463,
"is_parallel": true,
"self": 15.369327337164123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.92784777586894,
"count": 454630,
"is_parallel": true,
"self": 67.92784777586894
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 283.64557828601164,
"count": 45464,
"self": 0.9261088640196249,
"children": {
"process_trajectory": {
"total": 61.30246588799446,
"count": 45464,
"self": 60.31508072099359,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9873851670008662,
"count": 10,
"self": 0.9873851670008662
}
}
},
"_update_policy": {
"total": 221.41700353399756,
"count": 227,
"self": 88.60626136799101,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.81074216600655,
"count": 11574,
"self": 132.81074216600655
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.319998414663132e-07,
"count": 1,
"self": 8.319998414663132e-07
},
"TrainerController._save_models": {
"total": 0.0754820050001399,
"count": 1,
"self": 0.0006668520004495804,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07481515299969033,
"count": 1,
"self": 0.07481515299969033
}
}
}
}
}
}
}