poca-SoccerTwos / run_logs /timers.json
chandan9t8's picture
First Push
db5e14d
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.7923775911331177,
"min": 1.2698920965194702,
"max": 3.2957980632781982,
"count": 806
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 36421.11328125,
"min": 8977.853515625,
"max": 116445.515625,
"count": 806
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 227.27272727272728,
"min": 102.02127659574468,
"max": 999.0,
"count": 806
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 20000.0,
"min": 10336.0,
"max": 30180.0,
"count": 806
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1253.8392598742544,
"min": 1182.737984095324,
"max": 1256.9426942600808,
"count": 399
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 52661.248914718686,
"min": 2365.475968190648,
"max": 114550.30449282816,
"count": 399
},
"SoccerTwos.Step.mean": {
"value": 8059994.0,
"min": 9592.0,
"max": 8059994.0,
"count": 806
},
"SoccerTwos.Step.sum": {
"value": 8059994.0,
"min": 9592.0,
"max": 8059994.0,
"count": 806
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.039479829370975494,
"min": -0.10351750254631042,
"max": 0.08506845682859421,
"count": 806
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.7765922546386719,
"min": -4.338292598724365,
"max": 7.826297760009766,
"count": 806
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.04447450488805771,
"min": -0.09778528660535812,
"max": 0.08572176098823547,
"count": 806
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.0013527870178223,
"min": -4.477235794067383,
"max": 7.620918273925781,
"count": 806
},
"SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
"value": 2.0036182403564453,
"min": -0.08254619687795639,
"max": 6.25926399230957,
"count": 806
},
"SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
"value": 90.1628189086914,
"min": -1.2381925582885742,
"max": 208.9989776611328,
"count": 806
},
"SoccerTwos.Policy.CuriosityValueEstimate.mean": {
"value": 2.004000186920166,
"min": -0.08254672586917877,
"max": 6.266919136047363,
"count": 806
},
"SoccerTwos.Policy.CuriosityValueEstimate.sum": {
"value": 90.18000793457031,
"min": -1.2382009029388428,
"max": 208.61253356933594,
"count": 806
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 806
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 806
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.08472000095579359,
"min": -0.6316714286804199,
"max": 0.4004965490051385,
"count": 806
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -3.8124000430107117,
"min": -25.939599990844727,
"max": 21.52560019493103,
"count": 806
},
"SoccerTwos.Policy.CuriosityReward.mean": {
"value": 9.0308280924956,
"min": 0.0,
"max": 139.68406524658204,
"count": 806
},
"SoccerTwos.Policy.CuriosityReward.sum": {
"value": 406.387264162302,
"min": 0.0,
"max": 1549.0705833435059,
"count": 806
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.08472000095579359,
"min": -0.6316714286804199,
"max": 0.4004965490051385,
"count": 806
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -3.8124000430107117,
"min": -25.939599990844727,
"max": 21.52560019493103,
"count": 806
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 806
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 806
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.021437509487805075,
"min": 0.010982743279600981,
"max": 0.033023079589474945,
"count": 373
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.021437509487805075,
"min": 0.010982743279600981,
"max": 0.033023079589474945,
"count": 373
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.022745027486234904,
"min": 0.0015947921262219704,
"max": 0.7956314235925674,
"count": 373
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.022745027486234904,
"min": 0.0015947921262219704,
"max": 0.7956314235925674,
"count": 373
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.021885055117309093,
"min": 0.0016105484780079375,
"max": 4.344541382789612,
"count": 373
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.021885055117309093,
"min": 0.0016105484780079375,
"max": 4.344541382789612,
"count": 373
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0005,
"min": 0.0005,
"max": 0.0005,
"count": 373
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0005,
"min": 0.0005,
"max": 0.0005,
"count": 373
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.2,
"min": 0.19999999999999998,
"max": 0.2,
"count": 373
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.2,
"min": 0.19999999999999998,
"max": 0.2,
"count": 373
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 373
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 373
},
"SoccerTwos.Losses.CuriosityForwardLoss.mean": {
"value": 0.040013568568974735,
"min": 0.03822740530595183,
"max": 0.42451276381810504,
"count": 373
},
"SoccerTwos.Losses.CuriosityForwardLoss.sum": {
"value": 0.040013568568974735,
"min": 0.03822740530595183,
"max": 0.42451276381810504,
"count": 373
},
"SoccerTwos.Losses.CuriosityInverseLoss.mean": {
"value": 1.4960371464490891,
"min": 1.0168248653411864,
"max": 3.294746751586596,
"count": 373
},
"SoccerTwos.Losses.CuriosityInverseLoss.sum": {
"value": 1.4960371464490891,
"min": 1.0168248653411864,
"max": 3.294746751586596,
"count": 373
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689900679",
"python_version": "3.9.17 (main, Jul 5 2023, 16:17:03) \n[Clang 14.0.6 ]",
"command_line_arguments": "/Users/chandanakella/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0",
"numpy_version": "1.21.2",
"end_time_seconds": "1689946374"
},
"total": 42413.864084999,
"count": 1,
"self": 0.1933214169985149,
"children": {
"run_training.setup": {
"total": 0.018304333000000006,
"count": 1,
"self": 0.018304333000000006
},
"TrainerController.start_learning": {
"total": 42413.652459248995,
"count": 1,
"self": 4.826775452289439,
"children": {
"TrainerController._reset_env": {
"total": 7.675776332015207,
"count": 41,
"self": 7.675776332015207
},
"TrainerController.advance": {
"total": 42401.042389214694,
"count": 527268,
"self": 5.115270439418964,
"children": {
"env_step": {
"total": 6098.56102301845,
"count": 527268,
"self": 4748.646000808015,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1346.2372494135589,
"count": 527268,
"self": 27.901299883188585,
"children": {
"TorchPolicy.evaluate": {
"total": 1318.3359495303703,
"count": 1039934,
"self": 1318.3359495303703
}
}
},
"workers": {
"total": 3.677772796876674,
"count": 527268,
"self": 0.0,
"children": {
"worker_root": {
"total": 42361.793971211126,
"count": 527268,
"is_parallel": true,
"self": 38275.122066443204,
"children": {
"steps_from_proto": {
"total": 0.04987799998222098,
"count": 82,
"is_parallel": true,
"self": 0.008524203978739209,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.04135379600348177,
"count": 328,
"is_parallel": true,
"self": 0.04135379600348177
}
}
},
"UnityEnvironment.step": {
"total": 4086.62202676794,
"count": 527268,
"is_parallel": true,
"self": 184.17074008831514,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 106.1611776981036,
"count": 527268,
"is_parallel": true,
"self": 106.1611776981036
},
"communicator.exchange": {
"total": 3209.2057793575023,
"count": 527268,
"is_parallel": true,
"self": 3209.2057793575023
},
"steps_from_proto": {
"total": 587.0843296240193,
"count": 1054536,
"is_parallel": true,
"self": 88.1727119128982,
"children": {
"_process_rank_one_or_two_observation": {
"total": 498.91161771112115,
"count": 4218144,
"is_parallel": true,
"self": 498.91161771112115
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 36297.36609575683,
"count": 527268,
"self": 47.2659199536065,
"children": {
"process_trajectory": {
"total": 3000.676898395204,
"count": 527268,
"self": 2999.0388617692015,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6380366260023038,
"count": 16,
"self": 1.6380366260023038
}
}
},
"_update_policy": {
"total": 33249.423277408016,
"count": 374,
"self": 2917.163545759846,
"children": {
"TorchPOCAOptimizer.update": {
"total": 30332.25973164817,
"count": 14945,
"self": 30332.25973164817
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2500022421590984e-06,
"count": 1,
"self": 1.2500022421590984e-06
},
"TrainerController._save_models": {
"total": 0.10751699999673292,
"count": 1,
"self": 0.0007317079944186844,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10678529200231424,
"count": 1,
"self": 0.10678529200231424
}
}
}
}
}
}
}