ppo-SoccerTwos / run_logs /timers.json
DivyaMathi's picture
SoccerTwos
23898b9 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.9974749088287354,
"min": 2.9974749088287354,
"max": 3.2956607341766357,
"count": 100
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 66088.328125,
"min": 6396.58251953125,
"max": 105461.140625,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 106.06382978723404,
"min": 106.06382978723404,
"max": 999.0,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19940.0,
"min": 3932.0,
"max": 31140.0,
"count": 100
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1273.8085380823786,
"min": 1198.6174716687258,
"max": 1277.3410110223297,
"count": 95
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 119738.00257974358,
"min": 2398.5014391117093,
"max": 119738.00257974358,
"count": 95
},
"SoccerTwos.Step.mean": {
"value": 999962.0,
"min": 9154.0,
"max": 999962.0,
"count": 100
},
"SoccerTwos.Step.sum": {
"value": 999962.0,
"min": 9154.0,
"max": 999962.0,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.07389795035123825,
"min": -0.10200852900743484,
"max": 0.07389795035123825,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 6.946407318115234,
"min": -2.2129194736480713,
"max": 6.946407318115234,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.0805874615907669,
"min": -0.10194874554872513,
"max": 0.0805874615907669,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 7.575221538543701,
"min": -1.5446964502334595,
"max": 7.575221538543701,
"count": 100
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 100
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.03183404498911919,
"min": -0.5135789482217086,
"max": 0.4849199950695038,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -2.9924002289772034,
"min": -15.995199918746948,
"max": 22.343799889087677,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.03183404498911919,
"min": -0.5135789482217086,
"max": 0.4849199950695038,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -2.9924002289772034,
"min": -15.995199918746948,
"max": 22.343799889087677,
"count": 100
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.012011385384054545,
"min": 0.012011385384054545,
"max": 0.021126189133307587,
"count": 46
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.012011385384054545,
"min": 0.012011385384054545,
"max": 0.021126189133307587,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.03219428428759177,
"min": 0.0006587707262951881,
"max": 0.03346592703213294,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.03219428428759177,
"min": 0.0006587707262951881,
"max": 0.03346592703213294,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.03345832669486602,
"min": 0.0006634017641772516,
"max": 0.03437789970388015,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.03345832669486602,
"min": 0.0006634017641772516,
"max": 0.03437789970388015,
"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": 0.19999999999999996,
"max": 0.20000000000000007,
"count": 46
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.19999999999999996,
"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": "1710762958",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=/content/ml-agents/training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710768701"
},
"total": 5743.01368276,
"count": 1,
"self": 0.5926408400009677,
"children": {
"run_training.setup": {
"total": 0.11125427799970566,
"count": 1,
"self": 0.11125427799970566
},
"TrainerController.start_learning": {
"total": 5742.309787642,
"count": 1,
"self": 2.4826622968739684,
"children": {
"TrainerController._reset_env": {
"total": 3.3456743879996793,
"count": 5,
"self": 3.3456743879996793
},
"TrainerController.advance": {
"total": 5736.075324557127,
"count": 64930,
"self": 3.19147572791735,
"children": {
"env_step": {
"total": 2293.6117547480158,
"count": 64930,
"self": 1836.6036575718076,
"children": {
"SubprocessEnvManager._take_step": {
"total": 455.24884810410185,
"count": 64930,
"self": 20.723322526067932,
"children": {
"TorchPolicy.evaluate": {
"total": 434.5255255780339,
"count": 127852,
"self": 434.5255255780339
}
}
},
"workers": {
"total": 1.759249072106286,
"count": 64930,
"self": 0.0,
"children": {
"worker_root": {
"total": 5733.110537032871,
"count": 64930,
"is_parallel": true,
"self": 4228.503122180899,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004635517000224354,
"count": 2,
"is_parallel": true,
"self": 0.0012599299998328206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0033755870003915334,
"count": 8,
"is_parallel": true,
"self": 0.0033755870003915334
}
}
},
"UnityEnvironment.step": {
"total": 0.048861319000025105,
"count": 1,
"is_parallel": true,
"self": 0.0015393149997180444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009606470002836431,
"count": 1,
"is_parallel": true,
"self": 0.0009606470002836431
},
"communicator.exchange": {
"total": 0.04204100900005869,
"count": 1,
"is_parallel": true,
"self": 0.04204100900005869
},
"steps_from_proto": {
"total": 0.004320347999964724,
"count": 2,
"is_parallel": true,
"self": 0.0007774269997753436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0035429210001893807,
"count": 8,
"is_parallel": true,
"self": 0.0035429210001893807
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1504.5967189029748,
"count": 64929,
"is_parallel": true,
"self": 97.46312500119939,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 56.55590296596938,
"count": 64929,
"is_parallel": true,
"self": 56.55590296596938
},
"communicator.exchange": {
"total": 1059.4426095159288,
"count": 64929,
"is_parallel": true,
"self": 1059.4426095159288
},
"steps_from_proto": {
"total": 291.1350814198772,
"count": 129858,
"is_parallel": true,
"self": 51.72293713154795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 239.41214428832927,
"count": 519432,
"is_parallel": true,
"self": 239.41214428832927
}
}
}
}
},
"steps_from_proto": {
"total": 0.010695948998545646,
"count": 8,
"is_parallel": true,
"self": 0.0022001259999342437,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008495822998611402,
"count": 32,
"is_parallel": true,
"self": 0.008495822998611402
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 3439.2720940811932,
"count": 64930,
"self": 20.585026178173848,
"children": {
"process_trajectory": {
"total": 431.02383899401957,
"count": 64930,
"self": 430.3927720120191,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6310669820004478,
"count": 2,
"self": 0.6310669820004478
}
}
},
"_update_policy": {
"total": 2987.663228909,
"count": 46,
"self": 198.8538605919989,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2788.809368317001,
"count": 1395,
"self": 2788.809368317001
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5609994079568423e-06,
"count": 1,
"self": 1.5609994079568423e-06
},
"TrainerController._save_models": {
"total": 0.4061248389998582,
"count": 1,
"self": 0.006539617999806069,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3995852210000521,
"count": 1,
"self": 0.3995852210000521
}
}
}
}
}
}
}