poca-SoccerTwos / run_logs /timers.json
koenopok's picture
First Push
ab135a7 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.0180764198303223,
"min": 1.9686380624771118,
"max": 3.29573130607605,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 40942.734375,
"min": 23230.611328125,
"max": 127156.0390625,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 57.773809523809526,
"min": 46.25471698113208,
"max": 999.0,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19412.0,
"min": 16304.0,
"max": 24372.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1606.7540705210154,
"min": 1194.1876210015298,
"max": 1606.7540705210154,
"count": 483
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 269934.68384753057,
"min": 2392.4361146861966,
"max": 320537.73161546723,
"count": 483
},
"SoccerTwos.Step.mean": {
"value": 4999988.0,
"min": 9206.0,
"max": 4999988.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 4999988.0,
"min": 9206.0,
"max": 4999988.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.08221761882305145,
"min": -0.16408230364322662,
"max": 0.22671149671077728,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 13.812560081481934,
"min": -29.04256820678711,
"max": 28.614913940429688,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.081489697098732,
"min": -0.16812725365161896,
"max": 0.22300933301448822,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 13.690268516540527,
"min": -29.75852394104004,
"max": 29.2299747467041,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.17836428469135648,
"min": -0.5160571421895709,
"max": 0.5442823518725003,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 29.965199828147888,
"min": -62.956199645996094,
"max": 55.29199993610382,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.17836428469135648,
"min": -0.5160571421895709,
"max": 0.5442823518725003,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 29.965199828147888,
"min": -62.956199645996094,
"max": 55.29199993610382,
"count": 500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.018076893081888555,
"min": 0.011601724340289365,
"max": 0.02478181136199661,
"count": 238
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.018076893081888555,
"min": 0.011601724340289365,
"max": 0.02478181136199661,
"count": 238
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09370621119936308,
"min": 9.677321001314946e-06,
"max": 0.10801337112983068,
"count": 238
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09370621119936308,
"min": 9.677321001314946e-06,
"max": 0.10801337112983068,
"count": 238
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09552678316831589,
"min": 9.16501976462314e-06,
"max": 0.11014168585340182,
"count": 238
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09552678316831589,
"min": 9.16501976462314e-06,
"max": 0.11014168585340182,
"count": 238
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 238
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 238
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 238
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 238
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 238
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 238
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1726140025",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/ron/anaconda3/envs/rl/bin/mlagents-learn SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726143333"
},
"total": 3307.778840974999,
"count": 1,
"self": 0.16651327399449656,
"children": {
"run_training.setup": {
"total": 0.017641124002693687,
"count": 1,
"self": 0.017641124002693687
},
"TrainerController.start_learning": {
"total": 3307.594686577002,
"count": 1,
"self": 2.944197011049255,
"children": {
"TrainerController._reset_env": {
"total": 1.430085665993829,
"count": 25,
"self": 1.430085665993829
},
"TrainerController.advance": {
"total": 3303.1576436479554,
"count": 335444,
"self": 2.829188156807504,
"children": {
"env_step": {
"total": 2603.5166298651347,
"count": 335444,
"self": 1883.2772055045607,
"children": {
"SubprocessEnvManager._take_step": {
"total": 718.1913456719631,
"count": 335444,
"self": 21.45619433902175,
"children": {
"TorchPolicy.evaluate": {
"total": 696.7351513329413,
"count": 635164,
"self": 696.7351513329413
}
}
},
"workers": {
"total": 2.0480786886109854,
"count": 335444,
"self": 0.0,
"children": {
"worker_root": {
"total": 3303.6074121928505,
"count": 335444,
"is_parallel": true,
"self": 1771.8287012314358,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010473849979462102,
"count": 2,
"is_parallel": true,
"self": 0.00022717300089425407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008202119970519561,
"count": 8,
"is_parallel": true,
"self": 0.0008202119970519561
}
}
},
"UnityEnvironment.step": {
"total": 0.011166587999468902,
"count": 1,
"is_parallel": true,
"self": 0.00024985900017782114,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019514900122885592,
"count": 1,
"is_parallel": true,
"self": 0.00019514900122885592
},
"communicator.exchange": {
"total": 0.010036065999884158,
"count": 1,
"is_parallel": true,
"self": 0.010036065999884158
},
"steps_from_proto": {
"total": 0.0006855139981780667,
"count": 2,
"is_parallel": true,
"self": 0.0001331999992544297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000552313998923637,
"count": 8,
"is_parallel": true,
"self": 0.000552313998923637
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1531.7615807343973,
"count": 335443,
"is_parallel": true,
"self": 89.4693392949739,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 52.059525609489356,
"count": 335443,
"is_parallel": true,
"self": 52.059525609489356
},
"communicator.exchange": {
"total": 1156.2756498972412,
"count": 335443,
"is_parallel": true,
"self": 1156.2756498972412
},
"steps_from_proto": {
"total": 233.95706593269279,
"count": 670886,
"is_parallel": true,
"self": 43.36958953709109,
"children": {
"_process_rank_one_or_two_observation": {
"total": 190.5874763956017,
"count": 2683544,
"is_parallel": true,
"self": 190.5874763956017
}
}
}
}
},
"steps_from_proto": {
"total": 0.0171302270173328,
"count": 48,
"is_parallel": true,
"self": 0.003224001011403743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.013906226005929057,
"count": 192,
"is_parallel": true,
"self": 0.013906226005929057
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 696.8118256260132,
"count": 335444,
"self": 23.83871245248156,
"children": {
"process_trajectory": {
"total": 295.05417500857584,
"count": 335444,
"self": 294.34056990057434,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7136051080015022,
"count": 10,
"self": 0.7136051080015022
}
}
},
"_update_policy": {
"total": 377.91893816495576,
"count": 238,
"self": 246.29837315572877,
"children": {
"TorchPOCAOptimizer.update": {
"total": 131.620565009227,
"count": 7140,
"self": 131.620565009227
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.3200270738452673e-07,
"count": 1,
"self": 4.3200270738452673e-07
},
"TrainerController._save_models": {
"total": 0.06275982000079239,
"count": 1,
"self": 0.0005887779989279807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06217104200186441,
"count": 1,
"self": 0.06217104200186441
}
}
}
}
}
}
}