brendamareco's picture
First Push
0678e96
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7372627258300781,
"min": 0.720492422580719,
"max": 0.9062619209289551,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7031.2744140625,
"min": 7022.912109375,
"max": 9281.0283203125,
"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": 13.683553695678711,
"min": 12.637758255004883,
"max": 13.683553695678711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2668.29296875,
"min": 2451.72509765625,
"max": 2774.91357421875,
"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": 0.06875682364596858,
"min": 0.06199246449407428,
"max": 0.07200432964486489,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2750272945838743,
"min": 0.24796985797629711,
"max": 0.356971915055742,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18466053698577134,
"min": 0.17165757891009836,
"max": 0.22819913536602376,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7386421479430854,
"min": 0.6866303156403935,
"max": 1.0818692296743393,
"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": 26.90909090909091,
"min": 25.2,
"max": 27.072727272727274,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1184.0,
"min": 1122.0,
"max": 1489.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.90909090909091,
"min": 25.2,
"max": 27.072727272727274,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1184.0,
"min": 1122.0,
"max": 1489.0,
"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": "1696095536",
"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 --initialize-from=/content/ml-agents/results/SnowballTarget1 --run-id=SnowballTarget2 --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": "1696096016"
},
"total": 479.718631321,
"count": 1,
"self": 0.4244103759997415,
"children": {
"run_training.setup": {
"total": 0.06213907300025312,
"count": 1,
"self": 0.06213907300025312
},
"TrainerController.start_learning": {
"total": 479.232081872,
"count": 1,
"self": 0.5270411149922438,
"children": {
"TrainerController._reset_env": {
"total": 4.854033742999945,
"count": 1,
"self": 4.854033742999945
},
"TrainerController.advance": {
"total": 473.6999289970081,
"count": 18200,
"self": 0.27247913605378926,
"children": {
"env_step": {
"total": 473.4274498609543,
"count": 18200,
"self": 346.77306540189966,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.37963953402095,
"count": 18200,
"self": 1.969627325028796,
"children": {
"TorchPolicy.evaluate": {
"total": 124.41001220899216,
"count": 18200,
"self": 124.41001220899216
}
}
},
"workers": {
"total": 0.2747449250337013,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 477.6471350299962,
"count": 18200,
"is_parallel": true,
"self": 226.45185981400437,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003004566000072373,
"count": 1,
"is_parallel": true,
"self": 0.0008274920005533204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021770739995190524,
"count": 10,
"is_parallel": true,
"self": 0.0021770739995190524
}
}
},
"UnityEnvironment.step": {
"total": 0.03608712599998398,
"count": 1,
"is_parallel": true,
"self": 0.0006761150002603245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033042599989130395,
"count": 1,
"is_parallel": true,
"self": 0.00033042599989130395
},
"communicator.exchange": {
"total": 0.03200922999985778,
"count": 1,
"is_parallel": true,
"self": 0.03200922999985778
},
"steps_from_proto": {
"total": 0.0030713549999745737,
"count": 1,
"is_parallel": true,
"self": 0.0014233490001061,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016480059998684737,
"count": 10,
"is_parallel": true,
"self": 0.0016480059998684737
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.19527521599184,
"count": 18199,
"is_parallel": true,
"self": 10.533847962945856,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3728299440094816,
"count": 18199,
"is_parallel": true,
"self": 5.3728299440094816
},
"communicator.exchange": {
"total": 198.76547631601352,
"count": 18199,
"is_parallel": true,
"self": 198.76547631601352
},
"steps_from_proto": {
"total": 36.523120993022985,
"count": 18199,
"is_parallel": true,
"self": 6.7331858230841135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.78993516993887,
"count": 181990,
"is_parallel": true,
"self": 29.78993516993887
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011870999969687546,
"count": 1,
"self": 0.00011870999969687546,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.99283586605725,
"count": 451421,
"is_parallel": true,
"self": 10.03665422378117,
"children": {
"process_trajectory": {
"total": 255.49211806127641,
"count": 451421,
"is_parallel": true,
"self": 253.9762213562767,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5158967049997045,
"count": 4,
"is_parallel": true,
"self": 1.5158967049997045
}
}
},
"_update_policy": {
"total": 204.46406358099966,
"count": 90,
"is_parallel": true,
"self": 84.7677967870045,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.69626679399516,
"count": 4587,
"is_parallel": true,
"self": 119.69626679399516
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15095930699999371,
"count": 1,
"self": 0.0008660519997647498,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15009325500022896,
"count": 1,
"self": 0.15009325500022896
}
}
}
}
}
}
}