SoccerTwos1 / run_logs /timers.json
Christian90's picture
First Try
324b236
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.3338546752929688,
"min": 1.134285569190979,
"max": 3.2956857681274414,
"count": 1500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 45332.79296875,
"min": 9364.060546875,
"max": 167343.03125,
"count": 1500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 51.510416666666664,
"min": 41.724137931034484,
"max": 999.0,
"count": 1500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19780.0,
"min": 15400.0,
"max": 27432.0,
"count": 1500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1414.7833518495997,
"min": 1199.8789629969863,
"max": 1414.7833518495997,
"count": 650
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 271638.40355512314,
"min": 2401.4706074701407,
"max": 326351.28020636796,
"count": 650
},
"SoccerTwos.Step.mean": {
"value": 14999980.0,
"min": 9732.0,
"max": 14999980.0,
"count": 1500
},
"SoccerTwos.Step.sum": {
"value": 14999980.0,
"min": 9732.0,
"max": 14999980.0,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.10370947420597076,
"min": -0.1389545351266861,
"max": 0.14247018098831177,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -19.808509826660156,
"min": -21.398998260498047,
"max": 15.956660270690918,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.09783805906772614,
"min": -0.14363445341587067,
"max": 0.1409563422203064,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -18.687068939208984,
"min": -22.119705200195312,
"max": 15.653325080871582,
"count": 1500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.19421675536020888,
"min": -0.5425714275666645,
"max": 0.4322166641553243,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -37.095400273799896,
"min": -57.62279963493347,
"max": 32.04880005121231,
"count": 1500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.19421675536020888,
"min": -0.5425714275666645,
"max": 0.4322166641553243,
"count": 1500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -37.095400273799896,
"min": -57.62279963493347,
"max": 32.04880005121231,
"count": 1500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.018337363726459444,
"min": 0.01016525821663284,
"max": 0.025149818266315075,
"count": 696
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.018337363726459444,
"min": 0.01016525821663284,
"max": 0.025149818266315075,
"count": 696
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09707734659314156,
"min": 3.82567204767111e-10,
"max": 0.09707734659314156,
"count": 696
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09707734659314156,
"min": 3.82567204767111e-10,
"max": 0.09707734659314156,
"count": 696
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10036517803867658,
"min": 6.348822819320551e-10,
"max": 0.10036517803867658,
"count": 696
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10036517803867658,
"min": 6.348822819320551e-10,
"max": 0.10036517803867658,
"count": 696
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 696
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 696
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 696
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 696
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 696
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 696
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678980612",
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/ckahmann/miniconda3/envs/reinforcementlearning/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.30.0",
"mlagents_envs_version": "0.30.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679013420"
},
"total": 32807.81504894886,
"count": 1,
"self": 0.27023683581501245,
"children": {
"run_training.setup": {
"total": 0.013111628592014313,
"count": 1,
"self": 0.013111628592014313
},
"TrainerController.start_learning": {
"total": 32807.531700484455,
"count": 1,
"self": 21.50148303154856,
"children": {
"TrainerController._reset_env": {
"total": 18.976696708239615,
"count": 149,
"self": 18.976696708239615
},
"TrainerController.advance": {
"total": 32766.90164363943,
"count": 1023320,
"self": 20.295854567550123,
"children": {
"env_step": {
"total": 28289.99045867659,
"count": 1023320,
"self": 24784.38677883707,
"children": {
"SubprocessEnvManager._take_step": {
"total": 3493.4954940816388,
"count": 1023320,
"self": 118.81588698644191,
"children": {
"TorchPolicy.evaluate": {
"total": 3374.679607095197,
"count": 2017668,
"self": 3374.679607095197
}
}
},
"workers": {
"total": 12.108185757882893,
"count": 1023320,
"self": 0.0,
"children": {
"worker_root": {
"total": 32752.374596950598,
"count": 1023320,
"is_parallel": true,
"self": 10654.056678357534,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005172710865736008,
"count": 2,
"is_parallel": true,
"self": 0.0011349394917488098,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004037771373987198,
"count": 8,
"is_parallel": true,
"self": 0.004037771373987198
}
}
},
"UnityEnvironment.step": {
"total": 0.03992912918329239,
"count": 1,
"is_parallel": true,
"self": 0.0008681733161211014,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006876280531287193,
"count": 1,
"is_parallel": true,
"self": 0.0006876280531287193
},
"communicator.exchange": {
"total": 0.0356636019423604,
"count": 1,
"is_parallel": true,
"self": 0.0356636019423604
},
"steps_from_proto": {
"total": 0.002709725871682167,
"count": 2,
"is_parallel": true,
"self": 0.0004908563569188118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022188695147633553,
"count": 8,
"is_parallel": true,
"self": 0.0022188695147633553
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 22097.726475207135,
"count": 1023319,
"is_parallel": true,
"self": 1275.1264838725328,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 895.2564485482872,
"count": 1023319,
"is_parallel": true,
"self": 895.2564485482872
},
"communicator.exchange": {
"total": 16132.668494758196,
"count": 1023319,
"is_parallel": true,
"self": 16132.668494758196
},
"steps_from_proto": {
"total": 3794.675048028119,
"count": 2046638,
"is_parallel": true,
"self": 694.679800529033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3099.995247499086,
"count": 8186552,
"is_parallel": true,
"self": 3099.995247499086
}
}
}
}
},
"steps_from_proto": {
"total": 0.5914433859288692,
"count": 296,
"is_parallel": true,
"self": 0.11080232635140419,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.48064105957746506,
"count": 1184,
"is_parallel": true,
"self": 0.48064105957746506
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 4456.615330395289,
"count": 1023320,
"self": 181.36115091945976,
"children": {
"process_trajectory": {
"total": 1199.315489552915,
"count": 1023320,
"self": 1194.7139010010287,
"children": {
"RLTrainer._checkpoint": {
"total": 4.60158855188638,
"count": 30,
"self": 4.60158855188638
}
}
},
"_update_policy": {
"total": 3075.938689922914,
"count": 696,
"self": 1831.954083846882,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1243.984606076032,
"count": 20883,
"self": 1243.984606076032
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.044283509254456e-07,
"count": 1,
"self": 6.044283509254456e-07
},
"TrainerController._save_models": {
"total": 0.15187650080770254,
"count": 1,
"self": 0.0016095330938696861,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15026696771383286,
"count": 1,
"self": 0.15026696771383286
}
}
}
}
}
}
}