poca-SoccerTwos / run_logs /timers.json
chavicoski's picture
First model. Trained for 15M steps. Achieved a training ELO around 1800
22b7baf
raw
history blame
20.8 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 0.9358642101287842,
"min": 0.8890344500541687,
"max": 3.295703172683716,
"count": 1500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 17459.482421875,
"min": 16078.796875,
"max": 114315.078125,
"count": 1500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 51.824175824175825,
"min": 39.84426229508197,
"max": 999.0,
"count": 1500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 18864.0,
"min": 8308.0,
"max": 29016.0,
"count": 1500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1765.6470014398194,
"min": 1186.8332596690666,
"max": 1806.6922695638345,
"count": 1494
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 321347.7542620471,
"min": 2379.6541989372226,
"max": 421144.3781959489,
"count": 1494
},
"SoccerTwos.Step.mean": {
"value": 14999755.0,
"min": 9524.0,
"max": 14999755.0,
"count": 1500
},
"SoccerTwos.Step.sum": {
"value": 14999755.0,
"min": 9524.0,
"max": 14999755.0,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.04181674122810364,
"min": -0.13033989071846008,
"max": 0.17682650685310364,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -7.652463912963867,
"min": -25.416278839111328,
"max": 37.487220764160156,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.04168780520558357,
"min": -0.13259641826152802,
"max": 0.1779223382472992,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -7.628868103027344,
"min": -25.856300354003906,
"max": 37.71953582763672,
"count": 1500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.03824262345423464,
"min": -0.625,
"max": 0.4601304401522097,
"count": 1500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 6.998400092124939,
"min": -57.273400127887726,
"max": 73.17759996652603,
"count": 1500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.03824262345423464,
"min": -0.625,
"max": 0.4601304401522097,
"count": 1500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 6.998400092124939,
"min": -57.273400127887726,
"max": 73.17759996652603,
"count": 1500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01440862172312336,
"min": 0.010979887944085932,
"max": 0.022528246935689823,
"count": 724
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01440862172312336,
"min": 0.010979887944085932,
"max": 0.022528246935689823,
"count": 724
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.1151006082072854,
"min": 0.00014695349018438718,
"max": 0.12115517482161522,
"count": 724
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.1151006082072854,
"min": 0.00014695349018438718,
"max": 0.12115517482161522,
"count": 724
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.11522387862205505,
"min": 0.00014723005351697794,
"max": 0.12407925836741925,
"count": 724
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.11522387862205505,
"min": 0.00014723005351697794,
"max": 0.12407925836741925,
"count": 724
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 4.136998621333251e-07,
"min": 4.136998621333251e-07,
"max": 0.0002994488801837066,
"count": 724
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 4.136998621333251e-07,
"min": 4.136998621333251e-07,
"max": 0.0002994488801837066,
"count": 724
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.10013786666666666,
"min": 0.10013786666666666,
"max": 0.19981629333333334,
"count": 724
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.10013786666666666,
"min": 0.10013786666666666,
"max": 0.19981629333333334,
"count": 724
},
"SoccerTwos.Policy.Beta.mean": {
"value": 1.687954666666653e-05,
"min": 1.687954666666653e-05,
"max": 0.004990833037333334,
"count": 724
},
"SoccerTwos.Policy.Beta.sum": {
"value": 1.687954666666653e-05,
"min": 1.687954666666653e-05,
"max": 0.004990833037333334,
"count": 724
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676115595",
"python_version": "3.8.8 (default, Feb 24 2021, 21:46:12) \n[GCC 7.3.0]",
"command_line_arguments": "/opt/conda/bin/mlagents-learn ./src/SoccerTwos_params.yaml --env=ml-agents/training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=2023-02-11_11-39-53 --results-dir=./src/runs/train --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1",
"numpy_version": "1.19.2",
"end_time_seconds": "1676204506"
},
"total": 88910.341218623,
"count": 1,
"self": 0.2206141829956323,
"children": {
"run_training.setup": {
"total": 0.027713685000037458,
"count": 1,
"self": 0.027713685000037458
},
"TrainerController.start_learning": {
"total": 88910.092890755,
"count": 1,
"self": 17.07402022606402,
"children": {
"TrainerController._reset_env": {
"total": 9.99210184896441,
"count": 75,
"self": 9.99210184896441
},
"TrainerController.advance": {
"total": 88882.89476254096,
"count": 1032703,
"self": 15.194959447224392,
"children": {
"env_step": {
"total": 83035.61139679926,
"count": 1032703,
"self": 80116.75021078932,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2908.4984974555955,
"count": 1032703,
"self": 79.93895280152492,
"children": {
"TorchPolicy.evaluate": {
"total": 2828.5595446540706,
"count": 1886818,
"self": 584.5027858936355,
"children": {
"TorchPolicy.sample_actions": {
"total": 2244.056758760435,
"count": 1886818,
"self": 2244.056758760435
}
}
}
}
},
"workers": {
"total": 10.362688554344743,
"count": 1032703,
"self": 0.0,
"children": {
"worker_root": {
"total": 88886.24715045364,
"count": 1032703,
"is_parallel": true,
"self": 10667.448600943666,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007456541999999899,
"count": 2,
"is_parallel": true,
"self": 0.0009498299999108895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00650671200008901,
"count": 8,
"is_parallel": true,
"self": 0.00650671200008901
}
}
},
"UnityEnvironment.step": {
"total": 0.10457079700000804,
"count": 1,
"is_parallel": true,
"self": 0.00020912800005135068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0014572150000162765,
"count": 1,
"is_parallel": true,
"self": 0.0014572150000162765
},
"communicator.exchange": {
"total": 0.09752506799998173,
"count": 1,
"is_parallel": true,
"self": 0.09752506799998173
},
"steps_from_proto": {
"total": 0.005379385999958686,
"count": 2,
"is_parallel": true,
"self": 0.00035965099993973126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0050197350000189545,
"count": 8,
"is_parallel": true,
"self": 0.0050197350000189545
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 78218.40726014794,
"count": 1032702,
"is_parallel": true,
"self": 175.3986713180202,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1180.1439346548173,
"count": 1032702,
"is_parallel": true,
"self": 1180.1439346548173
},
"communicator.exchange": {
"total": 72705.24563847495,
"count": 1032702,
"is_parallel": true,
"self": 72705.24563847495
},
"steps_from_proto": {
"total": 4157.619015700161,
"count": 2065404,
"is_parallel": true,
"self": 287.17089562575165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3870.4481200744094,
"count": 8261616,
"is_parallel": true,
"self": 3870.4481200744094
}
}
}
}
},
"steps_from_proto": {
"total": 0.39128936202314435,
"count": 148,
"is_parallel": true,
"self": 0.026160716979347853,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.3651286450437965,
"count": 592,
"is_parallel": true,
"self": 0.3651286450437965
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 5832.088406294486,
"count": 1032703,
"self": 121.87381144145365,
"children": {
"process_trajectory": {
"total": 2224.404986121087,
"count": 1032703,
"self": 2220.3640772510926,
"children": {
"RLTrainer._checkpoint": {
"total": 4.040908869994382,
"count": 30,
"self": 4.040908869994382
}
}
},
"_update_policy": {
"total": 3485.809608731946,
"count": 724,
"self": 2572.2766864239197,
"children": {
"TorchPOCAOptimizer.update": {
"total": 913.5329223080262,
"count": 28972,
"self": 913.5329223080262
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.899936124682426e-07,
"count": 1,
"self": 6.899936124682426e-07
},
"TrainerController._save_models": {
"total": 0.13200544900610112,
"count": 1,
"self": 0.0008583279995946214,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1311471210065065,
"count": 1,
"self": 0.1311471210065065
}
}
}
}
}
}
}