poca-SoccerTwos / run_logs /timers.json
Armageddon
4M steps
d5c2d06 verified
raw
history blame
20.2 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.223773241043091,
"min": 2.0722453594207764,
"max": 2.236091136932373,
"count": 100
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 45258.234375,
"min": 38056.3828125,
"max": 50514.96875,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 77.578125,
"min": 51.44086021505376,
"max": 87.10344827586206,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19860.0,
"min": 18568.0,
"max": 20516.0,
"count": 100
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1488.8218073264109,
"min": 1468.8339752147765,
"max": 1508.8299624178053,
"count": 100
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 190569.1913377806,
"min": 172079.39408491494,
"max": 276200.57098956243,
"count": 100
},
"SoccerTwos.Step.mean": {
"value": 3999748.0,
"min": 3009969.0,
"max": 3999748.0,
"count": 100
},
"SoccerTwos.Step.sum": {
"value": 3999748.0,
"min": 3009969.0,
"max": 3999748.0,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0115288607776165,
"min": -0.1206521987915039,
"max": 0.09617013484239578,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.475694179534912,
"min": -20.629596710205078,
"max": 17.022113800048828,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.015976352617144585,
"min": -0.12377264350652695,
"max": 0.10104299336671829,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.044973134994507,
"min": -21.404094696044922,
"max": 17.88460922241211,
"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": -0.03146406123414636,
"min": -0.27117222133609986,
"max": 0.32952272575913055,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -4.027399837970734,
"min": -46.406399846076965,
"max": 43.49699980020523,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.03146406123414636,
"min": -0.27117222133609986,
"max": 0.32952272575913055,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -4.027399837970734,
"min": -46.406399846076965,
"max": 43.49699980020523,
"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": 0.026185355508156743,
"min": 0.020323997944554625,
"max": 0.03133109582704492,
"count": 96
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.026185355508156743,
"min": 0.020323997944554625,
"max": 0.03133109582704492,
"count": 96
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.08392822475483021,
"min": 0.08149543609470129,
"max": 0.1144369309147199,
"count": 96
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.08392822475483021,
"min": 0.08149543609470129,
"max": 0.1144369309147199,
"count": 96
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.08637854494154454,
"min": 0.08300136315325896,
"max": 0.11914086317022642,
"count": 96
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.08637854494154454,
"min": 0.08300136315325896,
"max": 0.11914086317022642,
"count": 96
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.00010000000000000003,
"min": 0.00010000000000000003,
"max": 0.00010000000000000003,
"count": 96
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.00010000000000000003,
"min": 0.00010000000000000003,
"max": 0.00010000000000000003,
"count": 96
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.30000000000000004,
"min": 0.30000000000000004,
"max": 0.30000000000000004,
"count": 96
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.30000000000000004,
"min": 0.30000000000000004,
"max": 0.30000000000000004,
"count": 96
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.010000000000000002,
"min": 0.010000000000000002,
"max": 0.010000000000000002,
"count": 96
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.010000000000000002,
"min": 0.010000000000000002,
"max": 0.010000000000000002,
"count": 96
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1718279492",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718282010"
},
"total": 2517.969767197,
"count": 1,
"self": 0.43776554199985185,
"children": {
"run_training.setup": {
"total": 0.0542554039998322,
"count": 1,
"self": 0.0542554039998322
},
"TrainerController.start_learning": {
"total": 2517.477746251,
"count": 1,
"self": 1.6043100350693749,
"children": {
"TrainerController._reset_env": {
"total": 2.372079333999409,
"count": 6,
"self": 2.372079333999409
},
"TrainerController.advance": {
"total": 2513.2097595329315,
"count": 68847,
"self": 1.6440261898642348,
"children": {
"env_step": {
"total": 1719.6449874930577,
"count": 68847,
"self": 1312.8831236869564,
"children": {
"SubprocessEnvManager._take_step": {
"total": 405.8213756830296,
"count": 68847,
"self": 9.936953617958352,
"children": {
"TorchPolicy.evaluate": {
"total": 395.88442206507125,
"count": 125724,
"self": 395.88442206507125
}
}
},
"workers": {
"total": 0.9404881230716455,
"count": 68847,
"self": 0.0,
"children": {
"worker_root": {
"total": 2512.8244949230334,
"count": 68847,
"is_parallel": true,
"self": 1408.677215260032,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003062387000227318,
"count": 2,
"is_parallel": true,
"self": 0.000803287000508135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002259099999719183,
"count": 8,
"is_parallel": true,
"self": 0.002259099999719183
}
}
},
"UnityEnvironment.step": {
"total": 0.03823810899984892,
"count": 1,
"is_parallel": true,
"self": 0.00118418300007761,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0008255600000666163,
"count": 1,
"is_parallel": true,
"self": 0.0008255600000666163
},
"communicator.exchange": {
"total": 0.03281173899995338,
"count": 1,
"is_parallel": true,
"self": 0.03281173899995338
},
"steps_from_proto": {
"total": 0.0034166269997513155,
"count": 2,
"is_parallel": true,
"self": 0.0007046189994071028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027120080003442126,
"count": 8,
"is_parallel": true,
"self": 0.0027120080003442126
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.01150233199905415,
"count": 10,
"is_parallel": true,
"self": 0.0023311429945351847,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.009171189004518965,
"count": 40,
"is_parallel": true,
"self": 0.009171189004518965
}
}
},
"UnityEnvironment.step": {
"total": 1104.1357773310024,
"count": 68846,
"is_parallel": true,
"self": 68.31497311213025,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 46.387385405968416,
"count": 68846,
"is_parallel": true,
"self": 46.387385405968416
},
"communicator.exchange": {
"total": 773.3335762869528,
"count": 68846,
"is_parallel": true,
"self": 773.3335762869528
},
"steps_from_proto": {
"total": 216.09984252595086,
"count": 137692,
"is_parallel": true,
"self": 36.31782842980056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 179.7820140961503,
"count": 550768,
"is_parallel": true,
"self": 179.7820140961503
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 791.9207458500096,
"count": 68847,
"self": 12.895249707110906,
"children": {
"process_trajectory": {
"total": 225.82177020290283,
"count": 68847,
"self": 225.14665546390233,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6751147390004917,
"count": 2,
"self": 0.6751147390004917
}
}
},
"_update_policy": {
"total": 553.2037259399958,
"count": 96,
"self": 297.6213310639955,
"children": {
"TorchPOCAOptimizer.update": {
"total": 255.5823948760003,
"count": 5760,
"self": 255.5823948760003
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.069999578059651e-07,
"count": 1,
"self": 9.069999578059651e-07
},
"TrainerController._save_models": {
"total": 0.2915964419999,
"count": 1,
"self": 0.0039638009993723244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28763264100052766,
"count": 1,
"self": 0.28763264100052766
}
}
}
}
}
}
}