poca-soccer_test / run_logs /timers.json
Varaprabha's picture
First Push
cc184f9
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.245697259902954,
"min": 3.226545572280884,
"max": 3.295748233795166,
"count": 38
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 73742.2421875,
"min": 23110.83984375,
"max": 105463.9453125,
"count": 38
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 637.0,
"min": 524.3333333333334,
"max": 999.0,
"count": 38
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 20384.0,
"min": 12584.0,
"max": 28060.0,
"count": 38
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1197.2585462071725,
"min": 1195.5989465768293,
"max": 1204.0900101178784,
"count": 35
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 14367.10255448607,
"min": 2392.052202047589,
"max": 16799.977600045375,
"count": 35
},
"SoccerTwos.Step.mean": {
"value": 379430.0,
"min": 9052.0,
"max": 379430.0,
"count": 38
},
"SoccerTwos.Step.sum": {
"value": 379430.0,
"min": 9052.0,
"max": 379430.0,
"count": 38
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.010683508589863777,
"min": -0.010683508589863777,
"max": 0.024976570159196854,
"count": 38
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.17093613743782043,
"min": -0.17093613743782043,
"max": 0.42459091544151306,
"count": 38
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.011709459125995636,
"min": -0.011709459125995636,
"max": 0.024996526539325714,
"count": 38
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.18735134601593018,
"min": -0.18735134601593018,
"max": 0.4248946011066437,
"count": 38
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 38
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 38
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.3323749974370003,
"min": -0.75,
"max": 0.3052857092448643,
"count": 38
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -5.317999958992004,
"min": -12.0,
"max": 4.273999929428101,
"count": 38
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.3323749974370003,
"min": -0.75,
"max": 0.3052857092448643,
"count": 38
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -5.317999958992004,
"min": -12.0,
"max": 4.273999929428101,
"count": 38
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 38
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.013147694972576573,
"min": 0.0129416783961157,
"max": 0.023816470261469172,
"count": 17
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.013147694972576573,
"min": 0.0129416783961157,
"max": 0.023816470261469172,
"count": 17
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.004678053020810088,
"min": 0.00042521934665273875,
"max": 0.006998291541822255,
"count": 17
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.004678053020810088,
"min": 0.00042521934665273875,
"max": 0.006998291541822255,
"count": 17
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.004676721524447203,
"min": 0.0004181344239138222,
"max": 0.0066053232798973715,
"count": 17
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.004676721524447203,
"min": 0.0004181344239138222,
"max": 0.0066053232798973715,
"count": 17
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 17
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 17
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 17
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 17
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 17
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 17
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687786766",
"python_version": "3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:08:06) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env /content/SoccerTwos/SoccerTwos.x86_64 --run-id=soccer_test --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": "1687794186"
},
"total": 7420.255562106,
"count": 1,
"self": 0.00662524399922404,
"children": {
"run_training.setup": {
"total": 0.026787066999986564,
"count": 1,
"self": 0.026787066999986564
},
"TrainerController.start_learning": {
"total": 7420.222149795,
"count": 1,
"self": 1.066164517073048,
"children": {
"TrainerController._reset_env": {
"total": 1.8385079839993068,
"count": 2,
"self": 1.8385079839993068
},
"TrainerController.advance": {
"total": 7416.804880079928,
"count": 25306,
"self": 1.121523095945122,
"children": {
"env_step": {
"total": 5998.640395356004,
"count": 25306,
"self": 5842.699268627952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.2549524549977,
"count": 25306,
"self": 7.050080318104847,
"children": {
"TorchPolicy.evaluate": {
"total": 148.20487213689285,
"count": 50166,
"self": 148.20487213689285
}
}
},
"workers": {
"total": 0.6861742730543483,
"count": 25305,
"self": 0.0,
"children": {
"worker_root": {
"total": 7405.769943673987,
"count": 25305,
"is_parallel": true,
"self": 1717.2165448910437,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0067336939998767775,
"count": 2,
"is_parallel": true,
"self": 0.0015793879999819183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005154305999894859,
"count": 8,
"is_parallel": true,
"self": 0.005154305999894859
}
}
},
"UnityEnvironment.step": {
"total": 0.4618275260000928,
"count": 1,
"is_parallel": true,
"self": 0.0006380020000733566,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.002966645000014978,
"count": 1,
"is_parallel": true,
"self": 0.002966645000014978
},
"communicator.exchange": {
"total": 0.44724146900000505,
"count": 1,
"is_parallel": true,
"self": 0.44724146900000505
},
"steps_from_proto": {
"total": 0.010981409999999414,
"count": 2,
"is_parallel": true,
"self": 0.0010119259999328278,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.009969484000066586,
"count": 8,
"is_parallel": true,
"self": 0.009969484000066586
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 5688.550346625942,
"count": 25304,
"is_parallel": true,
"self": 23.488668259907172,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 68.915948075002,
"count": 25304,
"is_parallel": true,
"self": 68.915948075002
},
"communicator.exchange": {
"total": 5417.003252685964,
"count": 25304,
"is_parallel": true,
"self": 5417.003252685964
},
"steps_from_proto": {
"total": 179.14247760506873,
"count": 50608,
"is_parallel": true,
"self": 31.0329844800292,
"children": {
"_process_rank_one_or_two_observation": {
"total": 148.10949312503953,
"count": 202432,
"is_parallel": true,
"self": 148.10949312503953
}
}
}
}
},
"steps_from_proto": {
"total": 0.0030521570006385446,
"count": 2,
"is_parallel": true,
"self": 0.0005738250029025949,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024783319977359497,
"count": 8,
"is_parallel": true,
"self": 0.0024783319977359497
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1417.042961627979,
"count": 25305,
"self": 11.053950031015347,
"children": {
"process_trajectory": {
"total": 172.9818535689658,
"count": 25305,
"self": 172.9818535689658
},
"_update_policy": {
"total": 1233.0071580279978,
"count": 18,
"self": 118.96013767800468,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1114.047020349993,
"count": 540,
"self": 1114.047020349993
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.8199998521595262e-06,
"count": 1,
"self": 1.8199998521595262e-06
},
"TrainerController._save_models": {
"total": 0.5125953940005274,
"count": 1,
"self": 0.002084393000586715,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5105110009999407,
"count": 1,
"self": 0.5105110009999407
}
}
}
}
}
}
}