dogukankartal's picture
First Push
8761781 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8103771209716797,
"min": 0.8103771209716797,
"max": 2.8653600215911865,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7737.48095703125,
"min": 7737.48095703125,
"max": 29344.15234375,
"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": 12.840264320373535,
"min": 0.2492784857749939,
"max": 12.840264320373535,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2503.8515625,
"min": 48.36002731323242,
"max": 2572.97509765625,
"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": 0.06704435091095923,
"min": 0.06334389539698154,
"max": 0.07609211325179785,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2681774036438369,
"min": 0.25337558158792617,
"max": 0.3804605662589893,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19589991480404256,
"min": 0.10978287180164353,
"max": 0.27378882475051225,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7835996592161703,
"min": 0.43913148720657413,
"max": 1.3419203524496042,
"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": 25.772727272727273,
"min": 3.0,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 132.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.0,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 132.0,
"max": 1382.0,
"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": "1721901272",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"command_line_arguments": "./ml-agents/mlagents/trainers/learn.py ./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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721901734"
},
"total": 462.53718026599995,
"count": 1,
"self": 0.43542966099994374,
"children": {
"run_training.setup": {
"total": 0.05986908599999197,
"count": 1,
"self": 0.05986908599999197
},
"TrainerController.start_learning": {
"total": 462.041881519,
"count": 1,
"self": 0.5560124680030185,
"children": {
"TrainerController._reset_env": {
"total": 2.4010112270000263,
"count": 1,
"self": 2.4010112270000263
},
"TrainerController.advance": {
"total": 458.99416989299704,
"count": 18200,
"self": 0.27183081899823947,
"children": {
"env_step": {
"total": 458.7223390739988,
"count": 18200,
"self": 298.13255117901514,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.29830216098878,
"count": 18200,
"self": 1.4932347489881295,
"children": {
"TorchPolicy.evaluate": {
"total": 158.80506741200065,
"count": 18200,
"self": 158.80506741200065
}
}
},
"workers": {
"total": 0.2914857339948753,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.7908381310059,
"count": 18200,
"is_parallel": true,
"self": 233.7311381730117,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006022271000006185,
"count": 1,
"is_parallel": true,
"self": 0.004414033999978528,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001608237000027657,
"count": 10,
"is_parallel": true,
"self": 0.001608237000027657
}
}
},
"UnityEnvironment.step": {
"total": 0.037568296000017654,
"count": 1,
"is_parallel": true,
"self": 0.0006722229999809315,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043939300002193704,
"count": 1,
"is_parallel": true,
"self": 0.00043939300002193704
},
"communicator.exchange": {
"total": 0.03427637300001152,
"count": 1,
"is_parallel": true,
"self": 0.03427637300001152
},
"steps_from_proto": {
"total": 0.0021803070000032676,
"count": 1,
"is_parallel": true,
"self": 0.00039603000004717615,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017842769999560915,
"count": 10,
"is_parallel": true,
"self": 0.0017842769999560915
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.0596999579942,
"count": 18199,
"is_parallel": true,
"self": 10.108173874005502,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.407141804993444,
"count": 18199,
"is_parallel": true,
"self": 5.407141804993444
},
"communicator.exchange": {
"total": 177.7424941509944,
"count": 18199,
"is_parallel": true,
"self": 177.7424941509944
},
"steps_from_proto": {
"total": 33.80189012800088,
"count": 18199,
"is_parallel": true,
"self": 6.424970945983603,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.376919182017275,
"count": 181990,
"is_parallel": true,
"self": 27.376919182017275
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001185599999189435,
"count": 1,
"self": 0.0001185599999189435,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 453.5439739250229,
"count": 610270,
"is_parallel": true,
"self": 13.53839283301403,
"children": {
"process_trajectory": {
"total": 253.61683599600866,
"count": 610270,
"is_parallel": true,
"self": 252.82779100500875,
"children": {
"RLTrainer._checkpoint": {
"total": 0.789044990999912,
"count": 4,
"is_parallel": true,
"self": 0.789044990999912
}
}
},
"_update_policy": {
"total": 186.3887450960002,
"count": 90,
"is_parallel": true,
"self": 57.783039445999805,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.6057056500004,
"count": 4587,
"is_parallel": true,
"self": 128.6057056500004
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09056937100001505,
"count": 1,
"self": 0.0009188590000803742,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08965051199993468,
"count": 1,
"self": 0.08965051199993468
}
}
}
}
}
}
}