poca-SoccerTwos / run_logs /timers.json
akter-sust's picture
First Push of the model
5aebe4b
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.2706055641174316,
"min": 3.268625259399414,
"max": 3.2957394123077393,
"count": 12
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 59132.546875,
"min": 52276.9140625,
"max": 105463.65625,
"count": 12
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 823.8571428571429,
"min": 652.625,
"max": 999.0,
"count": 12
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 23068.0,
"min": 15360.0,
"max": 26768.0,
"count": 12
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1197.475840993919,
"min": 1195.4520478544316,
"max": 1199.059293111055,
"count": 10
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 9579.806727951353,
"min": 2392.3318127809903,
"max": 11990.59293111055,
"count": 10
},
"SoccerTwos.Step.mean": {
"value": 119572.0,
"min": 9402.0,
"max": 119572.0,
"count": 12
},
"SoccerTwos.Step.sum": {
"value": 119572.0,
"min": 9402.0,
"max": 119572.0,
"count": 12
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.0019004932837560773,
"min": 0.0019004932837560773,
"max": 0.0398792065680027,
"count": 12
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.024706412106752396,
"min": 0.024706412106752396,
"max": 0.5726755857467651,
"count": 12
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.0021846292074769735,
"min": 0.0010205989237874746,
"max": 0.039207831025123596,
"count": 12
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.028400178998708725,
"min": 0.010205988772213459,
"max": 0.5488570332527161,
"count": 12
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 12
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 12
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.032461536618379444,
"min": -0.47266666491826376,
"max": 0.05710769158143263,
"count": 12
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -0.4219999760389328,
"min": -7.089999973773956,
"max": 0.7423999905586243,
"count": 12
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.032461536618379444,
"min": -0.47266666491826376,
"max": 0.05710769158143263,
"count": 12
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -0.4219999760389328,
"min": -7.089999973773956,
"max": 0.7423999905586243,
"count": 12
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.015744671378827964,
"min": 0.01418790725680689,
"max": 0.018454092300574605,
"count": 5
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.015744671378827964,
"min": 0.01418790725680689,
"max": 0.018454092300574605,
"count": 5
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0006894352365634405,
"min": 0.0006894352365634405,
"max": 0.0048208465178807575,
"count": 5
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0006894352365634405,
"min": 0.0006894352365634405,
"max": 0.0048208465178807575,
"count": 5
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.000687731834477745,
"min": 0.000687731834477745,
"max": 0.004877580748870969,
"count": 5
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.000687731834477745,
"min": 0.000687731834477745,
"max": 0.004877580748870969,
"count": 5
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 5
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 5
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 5
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 5
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 5
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1698713662",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn --force ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698713926"
},
"total": 264.298329126,
"count": 1,
"self": 0.13121345600006862,
"children": {
"run_training.setup": {
"total": 0.044995513000003484,
"count": 1,
"self": 0.044995513000003484
},
"TrainerController.start_learning": {
"total": 264.1221201569999,
"count": 1,
"self": 0.18519773300772613,
"children": {
"TrainerController._reset_env": {
"total": 3.7914921120000145,
"count": 1,
"self": 3.7914921120000145
},
"TrainerController.advance": {
"total": 259.85031827499233,
"count": 8147,
"self": 0.1966398389670303,
"children": {
"env_step": {
"total": 215.86300548101462,
"count": 8147,
"self": 165.28604526402023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 50.47271268899499,
"count": 8147,
"self": 1.2614391510014684,
"children": {
"TorchPolicy.evaluate": {
"total": 49.21127353799352,
"count": 16180,
"self": 49.21127353799352
}
}
},
"workers": {
"total": 0.10424752799940507,
"count": 8146,
"self": 0.0,
"children": {
"worker_root": {
"total": 263.4311377690001,
"count": 8146,
"is_parallel": true,
"self": 123.49749217199178,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029905369999596587,
"count": 2,
"is_parallel": true,
"self": 0.0008117020001918718,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002178834999767787,
"count": 8,
"is_parallel": true,
"self": 0.002178834999767787
}
}
},
"UnityEnvironment.step": {
"total": 0.0860958370001299,
"count": 1,
"is_parallel": true,
"self": 0.0012158919998910278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007762710001770756,
"count": 1,
"is_parallel": true,
"self": 0.0007762710001770756
},
"communicator.exchange": {
"total": 0.08074492400010058,
"count": 1,
"is_parallel": true,
"self": 0.08074492400010058
},
"steps_from_proto": {
"total": 0.003358749999961219,
"count": 2,
"is_parallel": true,
"self": 0.0005890740001177619,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027696759998434572,
"count": 8,
"is_parallel": true,
"self": 0.0027696759998434572
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 139.9336455970083,
"count": 8145,
"is_parallel": true,
"self": 9.235191483979406,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.898458851011583,
"count": 8145,
"is_parallel": true,
"self": 5.898458851011583
},
"communicator.exchange": {
"total": 96.90545755500943,
"count": 8145,
"is_parallel": true,
"self": 96.90545755500943
},
"steps_from_proto": {
"total": 27.894537707007885,
"count": 16290,
"is_parallel": true,
"self": 4.520242737005674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.37429497000221,
"count": 65160,
"is_parallel": true,
"self": 23.37429497000221
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 43.79067295501068,
"count": 8146,
"self": 1.727990671024827,
"children": {
"process_trajectory": {
"total": 13.309946795985752,
"count": 8146,
"self": 13.309946795985752
},
"_update_policy": {
"total": 28.7527354880001,
"count": 5,
"self": 17.664066019999836,
"children": {
"TorchPOCAOptimizer.update": {
"total": 11.088669468000262,
"count": 150,
"self": 11.088669468000262
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5250000160449417e-06,
"count": 1,
"self": 1.5250000160449417e-06
},
"TrainerController._save_models": {
"total": 0.2951105119998374,
"count": 1,
"self": 0.00205240899981618,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2930581030000212,
"count": 1,
"self": 0.2930581030000212
}
}
}
}
}
}
}