erniechiew's picture
Just running the notebook
5c150f9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9821121692657471,
"min": 0.9784815907478333,
"max": 2.8592588901519775,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9377.20703125,
"min": 9377.20703125,
"max": 29313.12109375,
"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": 12.736479759216309,
"min": 0.20231153070926666,
"max": 12.736479759216309,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2483.613525390625,
"min": 39.248435974121094,
"max": 2531.8125,
"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": 0.06855792130434066,
"min": 0.0631665806272341,
"max": 0.08001778866672277,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27423168521736263,
"min": 0.2595793320530242,
"max": 0.40008894333361383,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21968733278267522,
"min": 0.10203964108893393,
"max": 0.29439503772585995,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8787493311307009,
"min": 0.4081585643557357,
"max": 1.3175878352394292,
"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": 25.34090909090909,
"min": 2.7045454545454546,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 119.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 2.7045454545454546,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 119.0,
"max": 1400.0,
"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": "1675659770",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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=SnowballTarget2 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675660200"
},
"total": 430.4544296050001,
"count": 1,
"self": 0.37579147900009957,
"children": {
"run_training.setup": {
"total": 0.09720355900003597,
"count": 1,
"self": 0.09720355900003597
},
"TrainerController.start_learning": {
"total": 429.98143456699995,
"count": 1,
"self": 0.5281101079996233,
"children": {
"TrainerController._reset_env": {
"total": 9.933794382999963,
"count": 1,
"self": 9.933794382999963
},
"TrainerController.advance": {
"total": 419.3956760160004,
"count": 18201,
"self": 0.2518960800006198,
"children": {
"env_step": {
"total": 419.14377993599976,
"count": 18201,
"self": 275.33448190798913,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.54334103199164,
"count": 18201,
"self": 1.3576968759975898,
"children": {
"TorchPolicy.evaluate": {
"total": 142.18564415599405,
"count": 18201,
"self": 31.846017206984925,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.33962694900913,
"count": 18201,
"self": 110.33962694900913
}
}
}
}
},
"workers": {
"total": 0.2659569960189856,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 428.7757341350065,
"count": 18201,
"is_parallel": true,
"self": 206.9763540730205,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005946186000073794,
"count": 1,
"is_parallel": true,
"self": 0.0036428950003255522,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002303290999748242,
"count": 10,
"is_parallel": true,
"self": 0.002303290999748242
}
}
},
"UnityEnvironment.step": {
"total": 0.04204699299998538,
"count": 1,
"is_parallel": true,
"self": 0.000555032999955074,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035901599994758726,
"count": 1,
"is_parallel": true,
"self": 0.00035901599994758726
},
"communicator.exchange": {
"total": 0.039395325999976194,
"count": 1,
"is_parallel": true,
"self": 0.039395325999976194
},
"steps_from_proto": {
"total": 0.0017376180001065222,
"count": 1,
"is_parallel": true,
"self": 0.00041212099984022643,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013254970002662958,
"count": 10,
"is_parallel": true,
"self": 0.0013254970002662958
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.79938006198597,
"count": 18200,
"is_parallel": true,
"self": 8.305037294002204,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.95984341498945,
"count": 18200,
"is_parallel": true,
"self": 4.95984341498945
},
"communicator.exchange": {
"total": 176.18422804599152,
"count": 18200,
"is_parallel": true,
"self": 176.18422804599152
},
"steps_from_proto": {
"total": 32.3502713070028,
"count": 18200,
"is_parallel": true,
"self": 6.619875554014698,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.7303957529881,
"count": 182000,
"is_parallel": true,
"self": 25.7303957529881
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.612800012182561e-05,
"count": 1,
"self": 4.612800012182561e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 416.49953916493973,
"count": 336090,
"is_parallel": true,
"self": 8.976630443950171,
"children": {
"process_trajectory": {
"total": 240.99926925099078,
"count": 336090,
"is_parallel": true,
"self": 240.31695839299073,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6823108580000508,
"count": 4,
"is_parallel": true,
"self": 0.6823108580000508
}
}
},
"_update_policy": {
"total": 166.52363946999878,
"count": 90,
"is_parallel": true,
"self": 39.828610964996756,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.69502850500203,
"count": 4587,
"is_parallel": true,
"self": 126.69502850500203
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12380793199986329,
"count": 1,
"self": 0.000827417999971658,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12298051399989163,
"count": 1,
"self": 0.12298051399989163
}
}
}
}
}
}
}