atmikah's picture
First Push
c9abc83 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8770884275436401,
"min": 0.8705220818519592,
"max": 2.8715660572052,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8374.4404296875,
"min": 8374.4404296875,
"max": 29502.46875,
"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": 12.937908172607422,
"min": 0.4351467788219452,
"max": 12.937908172607422,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2522.89208984375,
"min": 84.41847229003906,
"max": 2625.46923828125,
"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": 0.06098666877520979,
"min": 0.05946532818328991,
"max": 0.07517067434702197,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24394667510083917,
"min": 0.24394667510083917,
"max": 0.3565594584632017,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2086042169408471,
"min": 0.12157505898800332,
"max": 0.2882145378081238,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8344168677633884,
"min": 0.48630023595201327,
"max": 1.3795693415198842,
"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": 25.204545454545453,
"min": 3.340909090909091,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 147.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.340909090909091,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 147.0,
"max": 1422.0,
"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": "1707501263",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707501696"
},
"total": 433.071281086,
"count": 1,
"self": 0.4408639749997292,
"children": {
"run_training.setup": {
"total": 0.049195949000022665,
"count": 1,
"self": 0.049195949000022665
},
"TrainerController.start_learning": {
"total": 432.58122116200025,
"count": 1,
"self": 0.5739709700342246,
"children": {
"TrainerController._reset_env": {
"total": 3.6365663770000083,
"count": 1,
"self": 3.6365663770000083
},
"TrainerController.advance": {
"total": 428.27416194896614,
"count": 18200,
"self": 0.2831854779669811,
"children": {
"env_step": {
"total": 427.99097647099916,
"count": 18200,
"self": 273.9492731559908,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.76103485599788,
"count": 18200,
"self": 1.4036981520143854,
"children": {
"TorchPolicy.evaluate": {
"total": 152.3573367039835,
"count": 18200,
"self": 152.3573367039835
}
}
},
"workers": {
"total": 0.2806684590104851,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 431.5614264740216,
"count": 18200,
"is_parallel": true,
"self": 216.69101120901792,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005396582000003036,
"count": 1,
"is_parallel": true,
"self": 0.00377609800011669,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016204839998863463,
"count": 10,
"is_parallel": true,
"self": 0.0016204839998863463
}
}
},
"UnityEnvironment.step": {
"total": 0.03833847600003537,
"count": 1,
"is_parallel": true,
"self": 0.0007546460001321975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004201100000500446,
"count": 1,
"is_parallel": true,
"self": 0.0004201100000500446
},
"communicator.exchange": {
"total": 0.03498542800002724,
"count": 1,
"is_parallel": true,
"self": 0.03498542800002724
},
"steps_from_proto": {
"total": 0.0021782919998258876,
"count": 1,
"is_parallel": true,
"self": 0.00041698199947859393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017613100003472937,
"count": 10,
"is_parallel": true,
"self": 0.0017613100003472937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.87041526500366,
"count": 18199,
"is_parallel": true,
"self": 10.658936677978318,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.247628149007369,
"count": 18199,
"is_parallel": true,
"self": 5.247628149007369
},
"communicator.exchange": {
"total": 165.8396975960302,
"count": 18199,
"is_parallel": true,
"self": 165.8396975960302
},
"steps_from_proto": {
"total": 33.12415284198778,
"count": 18199,
"is_parallel": true,
"self": 6.0156764359396675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.108476406048112,
"count": 181990,
"is_parallel": true,
"self": 27.108476406048112
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.752500010203221e-05,
"count": 1,
"self": 5.752500010203221e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 422.70602772406255,
"count": 668308,
"is_parallel": true,
"self": 14.431438130146717,
"children": {
"process_trajectory": {
"total": 232.10882560891355,
"count": 668308,
"is_parallel": true,
"self": 231.3103266259136,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7984989829999449,
"count": 4,
"is_parallel": true,
"self": 0.7984989829999449
}
}
},
"_update_policy": {
"total": 176.1657639850023,
"count": 90,
"is_parallel": true,
"self": 48.995312244995375,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.17045174000691,
"count": 4584,
"is_parallel": true,
"self": 127.17045174000691
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09646434099977341,
"count": 1,
"self": 0.0009898109997266147,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0954745300000468,
"count": 1,
"self": 0.0954745300000468
}
}
}
}
}
}
}