Pulting86's picture
initial commit
33726f8 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.2580041885375977,
"min": 3.256819248199463,
"max": 3.2958016395568848,
"count": 32
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 25959.77734375,
"min": 7304.44970703125,
"max": 105465.65625,
"count": 32
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 804.6666666666666,
"min": 514.0,
"max": 999.0,
"count": 32
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 9656.0,
"min": 5164.0,
"max": 25456.0,
"count": 32
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1199.9918937200964,
"min": 1198.995732238514,
"max": 1202.735771789421,
"count": 23
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 4799.967574880386,
"min": 2397.991464477028,
"max": 7200.478516744472,
"count": 23
},
"SoccerTwos.Step.mean": {
"value": 164312.0,
"min": 4744.0,
"max": 164312.0,
"count": 33
},
"SoccerTwos.Step.sum": {
"value": 164312.0,
"min": 4744.0,
"max": 164312.0,
"count": 33
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.01650661788880825,
"min": 0.014312711544334888,
"max": 0.01822400651872158,
"count": 33
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.0990397110581398,
"min": 0.07246498018503189,
"max": 0.17305231094360352,
"count": 33
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.015817852690815926,
"min": 0.0140229482203722,
"max": 0.018223991617560387,
"count": 33
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.09490711241960526,
"min": 0.0707668885588646,
"max": 0.1779646873474121,
"count": 33
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 33
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 33
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.2533999979496002,
"min": -0.6666666666666666,
"max": 0.3553142717906407,
"count": 33
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -1.5203999876976013,
"min": -4.0,
"max": 2.487199902534485,
"count": 33
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.2533999979496002,
"min": -0.6666666666666666,
"max": 0.3553142717906407,
"count": 33
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -1.5203999876976013,
"min": -4.0,
"max": 2.487199902534485,
"count": 33
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01186337743565673,
"min": 0.010897529197391122,
"max": 0.01186337743565673,
"count": 3
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01186337743565673,
"min": 0.010897529197391122,
"max": 0.01186337743565673,
"count": 3
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0018270743754692377,
"min": 0.001220637378282845,
"max": 0.0018299973267130554,
"count": 3
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0018270743754692377,
"min": 0.001220637378282845,
"max": 0.0018299973267130554,
"count": 3
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0022152574150823058,
"min": 0.0012257124634925277,
"max": 0.0022152574150823058,
"count": 3
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0022152574150823058,
"min": 0.0012257124634925277,
"max": 0.0022152574150823058,
"count": 3
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.00019747740126129998,
"min": 0.00019747740126129998,
"max": 0.00019916024041988003,
"count": 3
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.00019747740126129998,
"min": 0.00019747740126129998,
"max": 0.00019916024041988003,
"count": 3
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.14936934999999998,
"min": 0.14936934999999998,
"max": 0.14979005999999997,
"count": 3
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.14936934999999998,
"min": 0.14936934999999998,
"max": 0.14979005999999997,
"count": 3
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.00987399613,
"min": 0.00987399613,
"max": 0.009958053988000001,
"count": 3
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.00987399613,
"min": 0.00987399613,
"max": 0.009958053988000001,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1734649436",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./train-soccer/SoccerTwos.yaml --env=train-soccer/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwosNew --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734652495"
},
"total": 3058.635133326,
"count": 1,
"self": 0.011386746999505704,
"children": {
"run_training.setup": {
"total": 0.07107127599999785,
"count": 1,
"self": 0.07107127599999785
},
"TrainerController.start_learning": {
"total": 3058.5526753030003,
"count": 1,
"self": 0.43878770101900955,
"children": {
"TrainerController._reset_env": {
"total": 2.6530812839999953,
"count": 1,
"self": 2.6530812839999953
},
"TrainerController.advance": {
"total": 3053.430203829981,
"count": 10885,
"self": 0.47846000396475574,
"children": {
"env_step": {
"total": 432.10954788101014,
"count": 10885,
"self": 301.1996523030123,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.65958004299125,
"count": 10885,
"self": 2.7501590370086433,
"children": {
"TorchPolicy.evaluate": {
"total": 127.90942100598261,
"count": 21654,
"self": 127.90942100598261
}
}
},
"workers": {
"total": 0.25031553500662085,
"count": 10885,
"self": 0.0,
"children": {
"worker_root": {
"total": 2904.2377700600005,
"count": 10885,
"is_parallel": true,
"self": 2655.7367181999834,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0036195470000848218,
"count": 2,
"is_parallel": true,
"self": 0.0010192650000817594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026002820000030624,
"count": 8,
"is_parallel": true,
"self": 0.0026002820000030624
}
}
},
"UnityEnvironment.step": {
"total": 0.054792209999959596,
"count": 1,
"is_parallel": true,
"self": 0.001824118000058661,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.001034515000014835,
"count": 1,
"is_parallel": true,
"self": 0.001034515000014835
},
"communicator.exchange": {
"total": 0.047184622000031595,
"count": 1,
"is_parallel": true,
"self": 0.047184622000031595
},
"steps_from_proto": {
"total": 0.004748954999854504,
"count": 2,
"is_parallel": true,
"self": 0.0007823239999424914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003966630999912013,
"count": 8,
"is_parallel": true,
"self": 0.003966630999912013
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 248.50105186001701,
"count": 10884,
"is_parallel": true,
"self": 15.532492222001792,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.477288217003206,
"count": 10884,
"is_parallel": true,
"self": 10.477288217003206
},
"communicator.exchange": {
"total": 174.97494286499534,
"count": 10884,
"is_parallel": true,
"self": 174.97494286499534
},
"steps_from_proto": {
"total": 47.516328556016674,
"count": 21768,
"is_parallel": true,
"self": 8.244060707044355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.27226784897232,
"count": 87072,
"is_parallel": true,
"self": 39.27226784897232
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2620.842195945006,
"count": 10885,
"self": 3.075410431014461,
"children": {
"process_trajectory": {
"total": 186.38785183599225,
"count": 10885,
"self": 186.38785183599225
},
"_update_policy": {
"total": 2431.3789336779996,
"count": 4,
"self": 48.15287891499975,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2383.226054763,
"count": 160,
"self": 2383.226054763
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.8089999684889335e-06,
"count": 1,
"self": 1.8089999684889335e-06
},
"TrainerController._save_models": {
"total": 2.0306006790001447,
"count": 1,
"self": 0.9565477150003971,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0740529639997476,
"count": 1,
"self": 1.0740529639997476
}
}
}
}
}
}
}