DrishtiSharma's picture
SoccerTwos
cbca492
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.290503740310669,
"min": 3.2380189895629883,
"max": 3.2958366870880127,
"count": 50
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 123722.9375,
"min": 111062.5234375,
"max": 186043.390625,
"count": 50
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 809.8333333333334,
"min": 552.7777777777778,
"max": 999.0,
"count": 50
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 38872.0,
"min": 35216.0,
"max": 44484.0,
"count": 50
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1197.7071390595365,
"min": 1192.206128622398,
"max": 1202.1221479001772,
"count": 49
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 9581.657112476292,
"min": 2398.673808722595,
"max": 19216.31062616085,
"count": 49
},
"SoccerTwos.Step.mean": {
"value": 999887.0,
"min": 19170.0,
"max": 999887.0,
"count": 50
},
"SoccerTwos.Step.sum": {
"value": 999887.0,
"min": 19170.0,
"max": 999887.0,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.00854214932769537,
"min": -0.019583363085985184,
"max": -0.002443687990307808,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.20501157641410828,
"min": -0.5875008702278137,
"max": -0.04887375980615616,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.00854214932769537,
"min": -0.019583363085985184,
"max": -0.002443687990307808,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.20501157641410828,
"min": -0.5875008702278137,
"max": -0.04887375980615616,
"count": 50
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 50
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.16540833096951246,
"min": -0.3298000012125288,
"max": 0.2737142890691757,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 3.969799943268299,
"min": -9.234400033950806,
"max": 7.66400009393692,
"count": 50
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.16540833096951246,
"min": -0.3298000012125288,
"max": 0.2737142890691757,
"count": 50
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 3.969799943268299,
"min": -9.234400033950806,
"max": 7.66400009393692,
"count": 50
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01899933540262282,
"min": 0.012472235546738375,
"max": 0.02142047471522043,
"count": 46
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01899933540262282,
"min": 0.012472235546738375,
"max": 0.02142047471522043,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0007944911980303004,
"min": 7.506648590431079e-07,
"max": 0.005235202455272277,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0007944911980303004,
"min": 7.506648590431079e-07,
"max": 0.005235202455272277,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0007944911980303004,
"min": 7.506648590431079e-07,
"max": 0.005235202455272277,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0007944911980303004,
"min": 7.506648590431079e-07,
"max": 0.005235202455272277,
"count": 46
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 46
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 46
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 46
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 46
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 46
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 46
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680003653",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=./trained-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1680006486"
},
"total": 2833.202197866,
"count": 1,
"self": 0.4531878749999123,
"children": {
"run_training.setup": {
"total": 0.11015799099999413,
"count": 1,
"self": 0.11015799099999413
},
"TrainerController.start_learning": {
"total": 2832.638852,
"count": 1,
"self": 1.2747283039598187,
"children": {
"TrainerController._reset_env": {
"total": 11.546476255000243,
"count": 5,
"self": 11.546476255000243
},
"TrainerController.advance": {
"total": 2815.4575050130393,
"count": 64917,
"self": 1.5503823850099252,
"children": {
"env_step": {
"total": 2070.191032991002,
"count": 64917,
"self": 1251.467371606044,
"children": {
"SubprocessEnvManager._take_step": {
"total": 817.9198619869846,
"count": 64917,
"self": 10.879363151924622,
"children": {
"TorchPolicy.evaluate": {
"total": 807.04049883506,
"count": 128802,
"self": 807.04049883506
}
}
},
"workers": {
"total": 0.8037993979732505,
"count": 64917,
"self": 0.0,
"children": {
"worker_root": {
"total": 2819.5875314980044,
"count": 64917,
"is_parallel": true,
"self": 1760.4556102080287,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007107682000025761,
"count": 2,
"is_parallel": true,
"self": 0.004161089000035645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029465929999901164,
"count": 8,
"is_parallel": true,
"self": 0.0029465929999901164
}
}
},
"UnityEnvironment.step": {
"total": 0.03695120500003668,
"count": 1,
"is_parallel": true,
"self": 0.001017865000051188,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007782569999790212,
"count": 1,
"is_parallel": true,
"self": 0.0007782569999790212
},
"communicator.exchange": {
"total": 0.03203816600000664,
"count": 1,
"is_parallel": true,
"self": 0.03203816600000664
},
"steps_from_proto": {
"total": 0.0031169169999998303,
"count": 2,
"is_parallel": true,
"self": 0.0006377569999926891,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002479160000007141,
"count": 8,
"is_parallel": true,
"self": 0.002479160000007141
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1059.1246614599763,
"count": 64916,
"is_parallel": true,
"self": 63.4570706820366,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 44.23539136997249,
"count": 64916,
"is_parallel": true,
"self": 44.23539136997249
},
"communicator.exchange": {
"total": 753.8362381559796,
"count": 64916,
"is_parallel": true,
"self": 753.8362381559796
},
"steps_from_proto": {
"total": 197.59596125198772,
"count": 129832,
"is_parallel": true,
"self": 36.78918321085757,
"children": {
"_process_rank_one_or_two_observation": {
"total": 160.80677804113014,
"count": 519328,
"is_parallel": true,
"self": 160.80677804113014
}
}
}
}
},
"steps_from_proto": {
"total": 0.007259829999270551,
"count": 8,
"is_parallel": true,
"self": 0.0014563290000069173,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005803500999263633,
"count": 32,
"is_parallel": true,
"self": 0.005803500999263633
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 743.7160896370272,
"count": 64917,
"self": 15.96826185005989,
"children": {
"process_trajectory": {
"total": 153.06256203896652,
"count": 64917,
"self": 144.5021748789664,
"children": {
"RLTrainer._checkpoint": {
"total": 8.560387160000118,
"count": 2,
"self": 8.560387160000118
}
}
},
"_update_policy": {
"total": 574.6852657480007,
"count": 46,
"self": 178.897382380002,
"children": {
"TorchPOCAOptimizer.update": {
"total": 395.7878833679987,
"count": 1380,
"self": 395.7878833679987
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3630001376441214e-06,
"count": 1,
"self": 1.3630001376441214e-06
},
"TrainerController._save_models": {
"total": 4.3601410650003345,
"count": 1,
"self": 0.07851859500033243,
"children": {
"RLTrainer._checkpoint": {
"total": 4.281622470000002,
"count": 1,
"self": 4.281622470000002
}
}
}
}
}
}
}