Snowball-Target / run_logs /timers.json
Hans14's picture
First model using PPO
efbbec5
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2545795440673828,
"min": 1.2545795440673828,
"max": 2.8739047050476074,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12006.326171875,
"min": 12006.326171875,
"max": 29526.49609375,
"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": 11.365617752075195,
"min": 0.30022162199020386,
"max": 11.365617752075195,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2216.29541015625,
"min": 58.24299240112305,
"max": 2275.986328125,
"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": 0.04832665520734735,
"min": 0.03949260967116667,
"max": 0.05222352511433807,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.1933066208293894,
"min": 0.15797043868466668,
"max": 0.24717634468500668,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.24089352972805497,
"min": 0.09539079673898718,
"max": 0.2891138916214307,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9635741189122199,
"min": 0.3815631869559487,
"max": 1.4358085275938115,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.00029188200270599996,
"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": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.795454545454547,
"min": 2.6136363636363638,
"max": 22.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1003.0,
"min": 115.0,
"max": 1249.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.795454545454547,
"min": 2.6136363636363638,
"max": 22.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1003.0,
"min": 115.0,
"max": 1249.0,
"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": "1685865583",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "1685866062"
},
"total": 478.737289658,
"count": 1,
"self": 0.4338086459999886,
"children": {
"run_training.setup": {
"total": 0.04254125900001782,
"count": 1,
"self": 0.04254125900001782
},
"TrainerController.start_learning": {
"total": 478.260939753,
"count": 1,
"self": 0.6137033919937949,
"children": {
"TrainerController._reset_env": {
"total": 3.747079018000022,
"count": 1,
"self": 3.747079018000022
},
"TrainerController.advance": {
"total": 473.7483967640062,
"count": 18203,
"self": 0.30853274803303066,
"children": {
"env_step": {
"total": 473.43986401597317,
"count": 18203,
"self": 325.97330029895807,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.1587511749958,
"count": 18203,
"self": 2.002199407995022,
"children": {
"TorchPolicy.evaluate": {
"total": 145.1565517670008,
"count": 18203,
"self": 145.1565517670008
}
}
},
"workers": {
"total": 0.30781254201929187,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 476.58444069700226,
"count": 18203,
"is_parallel": true,
"self": 207.55730800100673,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007247516000006726,
"count": 1,
"is_parallel": true,
"self": 0.005672863999734545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015746520002721809,
"count": 10,
"is_parallel": true,
"self": 0.0015746520002721809
}
}
},
"UnityEnvironment.step": {
"total": 0.03685739200000171,
"count": 1,
"is_parallel": true,
"self": 0.0006085120000989264,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040824400002748007,
"count": 1,
"is_parallel": true,
"self": 0.00040824400002748007
},
"communicator.exchange": {
"total": 0.033616445000006934,
"count": 1,
"is_parallel": true,
"self": 0.033616445000006934
},
"steps_from_proto": {
"total": 0.0022241909998683695,
"count": 1,
"is_parallel": true,
"self": 0.0004112059993985895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00181298500046978,
"count": 10,
"is_parallel": true,
"self": 0.00181298500046978
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 269.02713269599553,
"count": 18202,
"is_parallel": true,
"self": 11.03610295999033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.81072380099431,
"count": 18202,
"is_parallel": true,
"self": 5.81072380099431
},
"communicator.exchange": {
"total": 213.61497310098503,
"count": 18202,
"is_parallel": true,
"self": 213.61497310098503
},
"steps_from_proto": {
"total": 38.56533283402587,
"count": 18202,
"is_parallel": true,
"self": 7.203685609117429,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.361647224908438,
"count": 182020,
"is_parallel": true,
"self": 31.361647224908438
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011691800000335206,
"count": 1,
"self": 0.00011691800000335206,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.7602917068966,
"count": 482572,
"is_parallel": true,
"self": 11.236163659868907,
"children": {
"process_trajectory": {
"total": 280.822632680027,
"count": 482572,
"is_parallel": true,
"self": 278.76094946002695,
"children": {
"RLTrainer._checkpoint": {
"total": 2.061683220000077,
"count": 4,
"is_parallel": true,
"self": 2.061683220000077
}
}
},
"_update_policy": {
"total": 177.7014953670007,
"count": 90,
"is_parallel": true,
"self": 75.02483352000672,
"children": {
"TorchPPOOptimizer.update": {
"total": 102.67666184699397,
"count": 2160,
"is_parallel": true,
"self": 102.67666184699397
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15164366099998006,
"count": 1,
"self": 0.000995151000097394,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15064850999988266,
"count": 1,
"self": 0.15064850999988266
}
}
}
}
}
}
}