DrishtiSharma's picture
SoccerTwos
3c8e177
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.192415475845337,
"min": 3.167081832885742,
"max": 3.2957563400268555,
"count": 50
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 162123.625,
"min": 106664.9140625,
"max": 200171.0625,
"count": 50
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 870.4166666666666,
"min": 628.3125,
"max": 999.0,
"count": 50
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 41780.0,
"min": 32044.0,
"max": 47148.0,
"count": 50
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1196.152248800052,
"min": 1191.0353937848483,
"max": 1200.7763188568224,
"count": 49
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 7176.913492800311,
"min": 2391.0917021297323,
"max": 16674.495512987876,
"count": 49
},
"SoccerTwos.Step.mean": {
"value": 999796.0,
"min": 19686.0,
"max": 999796.0,
"count": 50
},
"SoccerTwos.Step.sum": {
"value": 999796.0,
"min": 19686.0,
"max": 999796.0,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.004090842325240374,
"min": -0.029364680871367455,
"max": 0.004090842325240374,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.09408937394618988,
"min": -0.7341170310974121,
"max": 0.09408937394618988,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.0038251448422670364,
"min": -0.030881989747285843,
"max": 0.0038251448422670364,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.08797833323478699,
"min": -0.7314814925193787,
"max": 0.08797833323478699,
"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": -0.019269564877385677,
"min": -0.2608695652173913,
"max": 0.06984762066886538,
"count": 50
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -0.4431999921798706,
"min": -6.0,
"max": 1.466800034046173,
"count": 50
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.019269564877385677,
"min": -0.2608695652173913,
"max": 0.06984762066886538,
"count": 50
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -0.4431999921798706,
"min": -6.0,
"max": 1.466800034046173,
"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": 0.020385247551409216,
"min": 0.012534266071937358,
"max": 0.021648319139300536,
"count": 46
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.020385247551409216,
"min": 0.012534266071937358,
"max": 0.021648319139300536,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0002937910052423831,
"min": 3.3862912459881046e-06,
"max": 0.003981027162323395,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0002937910052423831,
"min": 3.3862912459881046e-06,
"max": 0.003981027162323395,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0002932540690380847,
"min": 3.785070445398257e-06,
"max": 0.003976371379879614,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0002932540690380847,
"min": 3.785070445398257e-06,
"max": 0.003976371379879614,
"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": 0.2,
"max": 0.20000000000000007,
"count": 46
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 46
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 46
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 46
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680007618",
"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": "1680009709"
},
"total": 2091.218630727,
"count": 1,
"self": 0.4386474909993012,
"children": {
"run_training.setup": {
"total": 0.19452839000018685,
"count": 1,
"self": 0.19452839000018685
},
"TrainerController.start_learning": {
"total": 2090.585454846,
"count": 1,
"self": 1.391797541015876,
"children": {
"TrainerController._reset_env": {
"total": 9.351715465000098,
"count": 5,
"self": 9.351715465000098
},
"TrainerController.advance": {
"total": 2079.5357683999846,
"count": 65163,
"self": 1.6076332349998665,
"children": {
"env_step": {
"total": 1675.0556232089684,
"count": 65163,
"self": 1317.0344876029267,
"children": {
"SubprocessEnvManager._take_step": {
"total": 357.16999204496574,
"count": 65163,
"self": 11.219571883900016,
"children": {
"TorchPolicy.evaluate": {
"total": 345.9504201610657,
"count": 129510,
"self": 345.9504201610657
}
}
},
"workers": {
"total": 0.8511435610760145,
"count": 65163,
"self": 0.0,
"children": {
"worker_root": {
"total": 2086.209372004003,
"count": 65163,
"is_parallel": true,
"self": 974.7328710039558,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006049875000144311,
"count": 2,
"is_parallel": true,
"self": 0.0035860910002156743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002463783999928637,
"count": 8,
"is_parallel": true,
"self": 0.002463783999928637
}
}
},
"UnityEnvironment.step": {
"total": 0.04102434399987942,
"count": 1,
"is_parallel": true,
"self": 0.0010606910000205971,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009033470000758825,
"count": 1,
"is_parallel": true,
"self": 0.0009033470000758825
},
"communicator.exchange": {
"total": 0.035675825999987865,
"count": 1,
"is_parallel": true,
"self": 0.035675825999987865
},
"steps_from_proto": {
"total": 0.003384479999795076,
"count": 2,
"is_parallel": true,
"self": 0.0006839709994892473,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027005090003058285,
"count": 8,
"is_parallel": true,
"self": 0.0027005090003058285
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1111.4677536650481,
"count": 65162,
"is_parallel": true,
"self": 64.744817255101,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 49.36126723694201,
"count": 65162,
"is_parallel": true,
"self": 49.36126723694201
},
"communicator.exchange": {
"total": 789.9855118390078,
"count": 65162,
"is_parallel": true,
"self": 789.9855118390078
},
"steps_from_proto": {
"total": 207.3761573339973,
"count": 130324,
"is_parallel": true,
"self": 38.25136385015435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 169.12479348384295,
"count": 521296,
"is_parallel": true,
"self": 169.12479348384295
}
}
}
}
},
"steps_from_proto": {
"total": 0.008747334999043233,
"count": 8,
"is_parallel": true,
"self": 0.0018297340011486085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006917600997894624,
"count": 32,
"is_parallel": true,
"self": 0.006917600997894624
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 402.8725119560163,
"count": 65163,
"self": 12.61089052490206,
"children": {
"process_trajectory": {
"total": 101.91156695711425,
"count": 65163,
"self": 101.43220182011419,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4793651370000589,
"count": 2,
"self": 0.4793651370000589
}
}
},
"_update_policy": {
"total": 288.350054474,
"count": 46,
"self": 180.13379086400982,
"children": {
"TorchPOCAOptimizer.update": {
"total": 108.21626360999016,
"count": 1383,
"self": 108.21626360999016
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.949999366654083e-07,
"count": 1,
"self": 9.949999366654083e-07
},
"TrainerController._save_models": {
"total": 0.3061724449999019,
"count": 1,
"self": 0.001884754000002431,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3042876909998995,
"count": 1,
"self": 0.3042876909998995
}
}
}
}
}
}
}