poca-SoccerTwos / run_logs /timers.json
jemal's picture
First Push
29f539f verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.1285617351531982,
"min": 2.057816505432129,
"max": 3.2957541942596436,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 49110.17578125,
"min": 9069.87890625,
"max": 132758.265625,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 88.1896551724138,
"min": 64.78947368421052,
"max": 999.0,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 20460.0,
"min": 10236.0,
"max": 31940.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1298.2108683814722,
"min": 1189.4901718224703,
"max": 1321.8724745551879,
"count": 470
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 150592.46073225077,
"min": 2380.8724584973256,
"max": 199724.71576437535,
"count": 470
},
"SoccerTwos.Step.mean": {
"value": 4999964.0,
"min": 9990.0,
"max": 4999964.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 4999964.0,
"min": 9990.0,
"max": 4999964.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.03608827292919159,
"min": -0.18706077337265015,
"max": 0.19841736555099487,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 4.150151252746582,
"min": -11.83333969116211,
"max": 16.27022361755371,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.03371202200651169,
"min": -0.2165866196155548,
"max": 0.21208561956882477,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 3.876882553100586,
"min": -12.097084045410156,
"max": 17.202173233032227,
"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": 0.14070086790167768,
"min": -0.7142857142857143,
"max": 0.44209999839464825,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 16.180599808692932,
"min": -40.87160015106201,
"max": 36.738800048828125,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.14070086790167768,
"min": -0.7142857142857143,
"max": 0.44209999839464825,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 16.180599808692932,
"min": -40.87160015106201,
"max": 36.738800048828125,
"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": 0.02955507180498292,
"min": 0.011747778230346739,
"max": 0.034086788580558885,
"count": 237
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.02955507180498292,
"min": 0.011747778230346739,
"max": 0.034086788580558885,
"count": 237
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.05991326433916887,
"min": 5.678832925089712e-06,
"max": 20.543557552372416,
"count": 237
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.05991326433916887,
"min": 5.678832925089712e-06,
"max": 20.543557552372416,
"count": 237
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.061352497711777684,
"min": 1.260669217420703e-05,
"max": 21.362492917881656,
"count": 237
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.061352497711777684,
"min": 1.260669217420703e-05,
"max": 21.362492917881656,
"count": 237
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.003000000000000001,
"min": 0.003000000000000001,
"max": 0.003000000000000001,
"count": 237
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.003000000000000001,
"min": 0.003000000000000001,
"max": 0.003000000000000001,
"count": 237
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 237
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 237
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 237
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 237
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1726630839",
"python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]",
"command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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",
"numpy_version": "1.23.5",
"end_time_seconds": "1726646269"
},
"total": 15429.667368709008,
"count": 1,
"self": 0.18624133401317522,
"children": {
"run_training.setup": {
"total": 0.017873500000860076,
"count": 1,
"self": 0.017873500000860076
},
"TrainerController.start_learning": {
"total": 15429.463253874994,
"count": 1,
"self": 2.5180560548760695,
"children": {
"TrainerController._reset_env": {
"total": 3.3113252080293023,
"count": 25,
"self": 3.3113252080293023
},
"TrainerController.advance": {
"total": 15423.545120988085,
"count": 329313,
"self": 2.219639240996912,
"children": {
"env_step": {
"total": 12495.226918487933,
"count": 329313,
"self": 12077.149996897017,
"children": {
"SubprocessEnvManager._take_step": {
"total": 416.3475366116254,
"count": 329313,
"self": 13.575165593458223,
"children": {
"TorchPolicy.evaluate": {
"total": 402.7723710181672,
"count": 636644,
"self": 402.7723710181672
}
}
},
"workers": {
"total": 1.7293849792913534,
"count": 329313,
"self": 0.0,
"children": {
"worker_root": {
"total": 15422.198863151498,
"count": 329313,
"is_parallel": true,
"self": 3715.2564296384007,
"children": {
"steps_from_proto": {
"total": 0.031976372956705745,
"count": 50,
"is_parallel": true,
"self": 0.0038239969726419076,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.028152375984063838,
"count": 200,
"is_parallel": true,
"self": 0.028152375984063838
}
}
},
"UnityEnvironment.step": {
"total": 11706.91045714014,
"count": 329313,
"is_parallel": true,
"self": 31.41189165905962,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 199.55579415091051,
"count": 329313,
"is_parallel": true,
"self": 199.55579415091051
},
"communicator.exchange": {
"total": 11081.685773227604,
"count": 329313,
"is_parallel": true,
"self": 11081.685773227604
},
"steps_from_proto": {
"total": 394.2569981025663,
"count": 658626,
"is_parallel": true,
"self": 42.48116707352165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 351.77583102904464,
"count": 2634504,
"is_parallel": true,
"self": 351.77583102904464
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2926.0985632591546,
"count": 329313,
"self": 31.865190188742417,
"children": {
"process_trajectory": {
"total": 496.8911444863479,
"count": 329313,
"self": 495.9638280683357,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9273164180121967,
"count": 10,
"self": 0.9273164180121967
}
}
},
"_update_policy": {
"total": 2397.3422285840643,
"count": 237,
"self": 276.4102660662684,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2120.931962517796,
"count": 7110,
"self": 2120.931962517796
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.9099464882165194e-07,
"count": 1,
"self": 2.9099464882165194e-07
},
"TrainerController._save_models": {
"total": 0.08875133300898597,
"count": 1,
"self": 0.0007229580078274012,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08802837500115857,
"count": 1,
"self": 0.08802837500115857
}
}
}
}
}
}
}