poca-SoccerTwos / run_logs /timers.json
refrtzd's picture
First Push
5512426 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.08760929107666,
"min": 2.005023241043091,
"max": 3.2382278442382812,
"count": 990
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 38545.6171875,
"min": 24562.78515625,
"max": 133265.328125,
"count": 990
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 61.88607594936709,
"min": 41.36065573770492,
"max": 999.0,
"count": 990
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19556.0,
"min": 2648.0,
"max": 23832.0,
"count": 990
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1616.128610047437,
"min": 1187.903283401041,
"max": 1633.8207147970363,
"count": 931
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 255348.32038749504,
"min": 2377.3295538096145,
"max": 385077.2517686916,
"count": 931
},
"SoccerTwos.Step.mean": {
"value": 9999969.0,
"min": 109834.0,
"max": 9999969.0,
"count": 990
},
"SoccerTwos.Step.sum": {
"value": 9999969.0,
"min": 109834.0,
"max": 9999969.0,
"count": 990
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.014052624814212322,
"min": -0.09026619791984558,
"max": 0.19964490830898285,
"count": 990
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -2.2343673706054688,
"min": -19.587764739990234,
"max": 25.220970153808594,
"count": 990
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.014127134345471859,
"min": -0.09066885709762573,
"max": 0.19929228723049164,
"count": 990
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.2462143898010254,
"min": -19.675142288208008,
"max": 25.31190299987793,
"count": 990
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 990
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 990
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.007655345418918057,
"min": -0.6560142849172864,
"max": 0.9501999914646149,
"count": 990
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -1.2171999216079712,
"min": -59.629999816417694,
"max": 54.13360011577606,
"count": 990
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.007655345418918057,
"min": -0.6560142849172864,
"max": 0.9501999914646149,
"count": 990
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -1.2171999216079712,
"min": -59.629999816417694,
"max": 54.13360011577606,
"count": 990
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 990
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 990
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.011126528695846597,
"min": 0.004657536279410124,
"max": 0.017648048838600515,
"count": 474
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.011126528695846597,
"min": 0.004657536279410124,
"max": 0.017648048838600515,
"count": 474
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.1176088109612465,
"min": 2.00031540771306e-06,
"max": 0.12602439473072688,
"count": 474
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.1176088109612465,
"min": 2.00031540771306e-06,
"max": 0.12602439473072688,
"count": 474
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.11820650398731232,
"min": 2.04935727197153e-06,
"max": 0.12671018143494925,
"count": 474
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.11820650398731232,
"min": 2.04935727197153e-06,
"max": 0.12671018143494925,
"count": 474
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 474
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 474
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 474
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 474
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 474
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 474
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1760602550",
"python_version": "3.10.13 (main, Oct 14 2025, 13:44:10) [GCC 14.2.0]",
"command_line_arguments": "/home/chames/mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760621031"
},
"total": 18481.230418270003,
"count": 1,
"self": 0.21978606300399406,
"children": {
"run_training.setup": {
"total": 0.015694204999817885,
"count": 1,
"self": 0.015694204999817885
},
"TrainerController.start_learning": {
"total": 18480.994938002,
"count": 1,
"self": 12.051065588424535,
"children": {
"TrainerController._reset_env": {
"total": 3.241110164000929,
"count": 50,
"self": 3.241110164000929
},
"TrainerController.advance": {
"total": 18465.48796825257,
"count": 670841,
"self": 13.63100686339385,
"children": {
"env_step": {
"total": 14323.661616965026,
"count": 670841,
"self": 8941.614945890014,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5374.242327235592,
"count": 670841,
"self": 83.61775653585028,
"children": {
"TorchPolicy.evaluate": {
"total": 5290.6245706997415,
"count": 1254216,
"self": 5290.6245706997415
}
}
},
"workers": {
"total": 7.804343839419744,
"count": 670841,
"self": 0.0,
"children": {
"worker_root": {
"total": 18451.06757879113,
"count": 670841,
"is_parallel": true,
"self": 10867.19526391635,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020017100005134125,
"count": 2,
"is_parallel": true,
"self": 0.0005758349998359336,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001425875000677479,
"count": 8,
"is_parallel": true,
"self": 0.001425875000677479
}
}
},
"UnityEnvironment.step": {
"total": 0.02295448099994246,
"count": 1,
"is_parallel": true,
"self": 0.00038358599977073027,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002751809997789678,
"count": 1,
"is_parallel": true,
"self": 0.0002751809997789678
},
"communicator.exchange": {
"total": 0.021062306000203534,
"count": 1,
"is_parallel": true,
"self": 0.021062306000203534
},
"steps_from_proto": {
"total": 0.001233408000189229,
"count": 2,
"is_parallel": true,
"self": 0.0003261640003984212,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009072439997908077,
"count": 8,
"is_parallel": true,
"self": 0.0009072439997908077
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 7583.8239489437765,
"count": 670840,
"is_parallel": true,
"self": 223.1551697226132,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 142.415077002006,
"count": 670840,
"is_parallel": true,
"self": 142.415077002006
},
"communicator.exchange": {
"total": 6589.699458512546,
"count": 670840,
"is_parallel": true,
"self": 6589.699458512546
},
"steps_from_proto": {
"total": 628.5542437066115,
"count": 1341680,
"is_parallel": true,
"self": 123.69599916198331,
"children": {
"_process_rank_one_or_two_observation": {
"total": 504.8582445446282,
"count": 5366720,
"is_parallel": true,
"self": 504.8582445446282
}
}
}
}
},
"steps_from_proto": {
"total": 0.048365931005719176,
"count": 98,
"is_parallel": true,
"self": 0.009323374009909458,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.03904255699580972,
"count": 392,
"is_parallel": true,
"self": 0.03904255699580972
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 4128.195344424152,
"count": 670841,
"self": 90.85343010582164,
"children": {
"process_trajectory": {
"total": 2076.960772995323,
"count": 670841,
"self": 2072.7492667063198,
"children": {
"RLTrainer._checkpoint": {
"total": 4.21150628900341,
"count": 20,
"self": 4.21150628900341
}
}
},
"_update_policy": {
"total": 1960.381141323007,
"count": 474,
"self": 922.3429677562108,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1038.038173566796,
"count": 7110,
"self": 1038.038173566796
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.260015652514994e-07,
"count": 1,
"self": 6.260015652514994e-07
},
"TrainerController._save_models": {
"total": 0.21479337100026896,
"count": 1,
"self": 0.002412013000139268,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2123813580001297,
"count": 1,
"self": 0.2123813580001297
}
}
}
}
}
}
}