poca-SoccerTwos / run_logs /timers.json
Ari8's picture
First Push
9d2f99a verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.6559860706329346,
"min": 2.6286559104919434,
"max": 3.295727491378784,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 56009.43359375,
"min": 21099.6328125,
"max": 133365.21875,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 61.4375,
"min": 48.43,
"max": 999.0,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19660.0,
"min": 16892.0,
"max": 23492.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1686.6837182634747,
"min": 1198.7251530025292,
"max": 1686.6837182634747,
"count": 495
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 269869.39492215595,
"min": 2397.4503060050583,
"max": 321601.42391308583,
"count": 495
},
"SoccerTwos.Step.mean": {
"value": 4999964.0,
"min": 9422.0,
"max": 4999964.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 4999964.0,
"min": 9422.0,
"max": 4999964.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.014134632423520088,
"min": -0.09138451516628265,
"max": 0.2078404724597931,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 2.2756757736206055,
"min": -14.9534912109375,
"max": 30.53224754333496,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.014011605642735958,
"min": -0.09226340800523758,
"max": 0.21600241959095,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 2.255868434906006,
"min": -13.835221290588379,
"max": 30.643539428710938,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.04954037273892705,
"min": -0.5714285714285714,
"max": 0.5578275865008091,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -7.976000010967255,
"min": -74.29000002145767,
"max": 62.00960040092468,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.04954037273892705,
"min": -0.5714285714285714,
"max": 0.5578275865008091,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -7.976000010967255,
"min": -74.29000002145767,
"max": 62.00960040092468,
"count": 500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.021063554284046403,
"min": 0.011607398350800697,
"max": 0.022669363021850585,
"count": 240
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.021063554284046403,
"min": 0.011607398350800697,
"max": 0.022669363021850585,
"count": 240
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.04847050793468952,
"min": 5.573062929518831e-05,
"max": 0.06007662825286388,
"count": 240
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.04847050793468952,
"min": 5.573062929518831e-05,
"max": 0.06007662825286388,
"count": 240
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.05020802939931552,
"min": 5.4799235052390334e-05,
"max": 0.06286230633656184,
"count": 240
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.05020802939931552,
"min": 5.4799235052390334e-05,
"max": 0.06286230633656184,
"count": 240
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 240
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 240
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.10000000000000003,
"min": 0.1,
"max": 0.10000000000000003,
"count": 240
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.10000000000000003,
"min": 0.1,
"max": 0.10000000000000003,
"count": 240
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.008000000000000002,
"min": 0.008,
"max": 0.008000000000000002,
"count": 240
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.008000000000000002,
"min": 0.008,
"max": 0.008000000000000002,
"count": 240
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1743030712",
"python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "\\\\?\\C:\\Users\\Paola\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn C:\\Users\\Paola\\Documents\\OBJETIVOS\\DEEP_LEARNING\\RL\\unit7\\SoccerTwos.yaml --env=./SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1743051428"
},
"total": 20716.615412300103,
"count": 1,
"self": 3.653950000065379,
"children": {
"run_training.setup": {
"total": 0.13232370000332594,
"count": 1,
"self": 0.13232370000332594
},
"TrainerController.start_learning": {
"total": 20712.829138600035,
"count": 1,
"self": 15.572188598918729,
"children": {
"TrainerController._reset_env": {
"total": 6.81984509981703,
"count": 25,
"self": 6.81984509981703
},
"TrainerController.advance": {
"total": 20690.21463510138,
"count": 337211,
"self": 15.957880300236866,
"children": {
"env_step": {
"total": 10661.463299968163,
"count": 337211,
"self": 8597.163777963142,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2055.23977868387,
"count": 337211,
"self": 79.31644735031296,
"children": {
"TorchPolicy.evaluate": {
"total": 1975.9233313335571,
"count": 632690,
"self": 1975.9233313335571
}
}
},
"workers": {
"total": 9.059743321151473,
"count": 337211,
"self": 0.0,
"children": {
"worker_root": {
"total": 20687.74216215068,
"count": 337211,
"is_parallel": true,
"self": 13804.323674601968,
"children": {
"steps_from_proto": {
"total": 0.07895689993165433,
"count": 50,
"is_parallel": true,
"self": 0.016222999896854162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.06273390003480017,
"count": 200,
"is_parallel": true,
"self": 0.06273390003480017
}
}
},
"UnityEnvironment.step": {
"total": 6883.33953064878,
"count": 337211,
"is_parallel": true,
"self": 323.45164394786116,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 256.4322083761217,
"count": 337211,
"is_parallel": true,
"self": 256.4322083761217
},
"communicator.exchange": {
"total": 5261.944040477509,
"count": 337211,
"is_parallel": true,
"self": 5261.944040477509
},
"steps_from_proto": {
"total": 1041.5116378472885,
"count": 674422,
"is_parallel": true,
"self": 217.03753970377147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 824.474098143517,
"count": 2697688,
"is_parallel": true,
"self": 824.474098143517
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 10012.79345483298,
"count": 337211,
"self": 94.62343006615993,
"children": {
"process_trajectory": {
"total": 1850.3375357671175,
"count": 337211,
"self": 1848.0443905671127,
"children": {
"RLTrainer._checkpoint": {
"total": 2.293145200004801,
"count": 10,
"self": 2.293145200004801
}
}
},
"_update_policy": {
"total": 8067.832488999702,
"count": 240,
"self": 1276.3936460042605,
"children": {
"TorchPOCAOptimizer.update": {
"total": 6791.4388429954415,
"count": 7203,
"self": 6791.4388429954415
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6998965293169022e-06,
"count": 1,
"self": 1.6998965293169022e-06
},
"TrainerController._save_models": {
"total": 0.2224681000225246,
"count": 1,
"self": 0.026839799946174026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19562830007635057,
"count": 1,
"self": 0.19562830007635057
}
}
}
}
}
}
}