poca-SoccerTwos / run_logs /timers.json
monti-python's picture
First training for SoccerTwos
e6ae781 verified
raw
history blame
20.1 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.147171974182129,
"min": 3.0757153034210205,
"max": 3.2128803730010986,
"count": 100
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 32932.0078125,
"min": 7447.50390625,
"max": 158240.28125,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 915.8333333333334,
"min": 405.90909090909093,
"max": 999.0,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 21980.0,
"min": 3700.0,
"max": 27856.0,
"count": 100
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1197.294585587241,
"min": 1197.294585587241,
"max": 1213.8097241010091,
"count": 91
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 4789.178342348964,
"min": 2402.3416809606965,
"max": 19353.100026898544,
"count": 91
},
"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.Step.mean": {
"value": 1639180.0,
"min": 659202.0,
"max": 1639180.0,
"count": 99
},
"SoccerTwos.Step.sum": {
"value": 1639180.0,
"min": 659202.0,
"max": 1639180.0,
"count": 99
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.015390798449516296,
"min": -0.018517760559916496,
"max": 0.016770390793681145,
"count": 99
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.16929878294467926,
"min": -0.2552330493927002,
"max": 0.18447428941726685,
"count": 99
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.01509619690477848,
"min": -0.018388936296105385,
"max": 0.017871476709842682,
"count": 99
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.16605816781520844,
"min": -0.2526383399963379,
"max": 0.1965862363576889,
"count": 99
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 99
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 99
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.36363636363636365,
"min": -0.5,
"max": 0.45713333288828534,
"count": 99
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -4.0,
"min": -7.0,
"max": 8.228399991989136,
"count": 99
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.36363636363636365,
"min": -0.5,
"max": 0.45713333288828534,
"count": 99
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -4.0,
"min": -7.0,
"max": 8.228399991989136,
"count": 99
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.016261281779346368,
"min": 0.013237021410410913,
"max": 0.02583168828083823,
"count": 46
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.016261281779346368,
"min": 0.013237021410410913,
"max": 0.02583168828083823,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0046276195285220945,
"min": 0.00021013136767688786,
"max": 0.006187491274128358,
"count": 46
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0046276195285220945,
"min": 0.00021013136767688786,
"max": 0.006187491274128358,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.004642315007125338,
"min": 0.00020933844318664563,
"max": 0.006221231569846471,
"count": 46
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.004642315007125338,
"min": 0.00020933844318664563,
"max": 0.006221231569846471,
"count": 46
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 46
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 46
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 46
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 46
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 46
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 46
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1724450679",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/poca/SoccerTwos_monti-python.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics --resume",
"mlagents_version": "1.0.0",
"mlagents_envs_version": "1.0.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.21.2",
"end_time_seconds": "1724453053"
},
"total": 2374.332812839988,
"count": 1,
"self": 0.3011273759766482,
"children": {
"run_training.setup": {
"total": 0.023536217006039806,
"count": 1,
"self": 0.023536217006039806
},
"TrainerController.start_learning": {
"total": 2374.0081492470053,
"count": 1,
"self": 1.4943843034125166,
"children": {
"TrainerController._reset_env": {
"total": 5.1240192109689815,
"count": 6,
"self": 5.1240192109689815
},
"TrainerController.advance": {
"total": 2367.0536718156363,
"count": 64664,
"self": 1.674688027051161,
"children": {
"env_step": {
"total": 1924.810803599612,
"count": 64664,
"self": 1164.4117003164429,
"children": {
"SubprocessEnvManager._take_step": {
"total": 759.3363031045301,
"count": 64664,
"self": 13.485134564500186,
"children": {
"TorchPolicy.evaluate": {
"total": 745.8511685400299,
"count": 128325,
"self": 745.8511685400299
}
}
},
"workers": {
"total": 1.0628001786390087,
"count": 64663,
"self": 0.0,
"children": {
"worker_root": {
"total": 2370.424527122552,
"count": 64663,
"is_parallel": true,
"self": 1379.279040477617,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0037540920020546764,
"count": 2,
"is_parallel": true,
"self": 0.0011440380185376853,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002610053983516991,
"count": 8,
"is_parallel": true,
"self": 0.002610053983516991
}
}
},
"UnityEnvironment.step": {
"total": 0.027154524010256864,
"count": 1,
"is_parallel": true,
"self": 0.0004653770010918379,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005320620111888275,
"count": 1,
"is_parallel": true,
"self": 0.0005320620111888275
},
"communicator.exchange": {
"total": 0.024583517006249167,
"count": 1,
"is_parallel": true,
"self": 0.024583517006249167
},
"steps_from_proto": {
"total": 0.0015735679917270318,
"count": 2,
"is_parallel": true,
"self": 0.00035226598265580833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012213020090712234,
"count": 8,
"is_parallel": true,
"self": 0.0012213020090712234
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.007678079025936313,
"count": 10,
"is_parallel": true,
"self": 0.0017173930536955595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0059606859722407535,
"count": 40,
"is_parallel": true,
"self": 0.0059606859722407535
}
}
},
"UnityEnvironment.step": {
"total": 991.1378085659089,
"count": 64662,
"is_parallel": true,
"self": 32.84578116021294,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.35030674104928,
"count": 64662,
"is_parallel": true,
"self": 21.35030674104928
},
"communicator.exchange": {
"total": 832.1024990279402,
"count": 64662,
"is_parallel": true,
"self": 832.1024990279402
},
"steps_from_proto": {
"total": 104.8392216367065,
"count": 129324,
"is_parallel": true,
"self": 22.7072764007753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.1319452359312,
"count": 517296,
"is_parallel": true,
"self": 82.1319452359312
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 440.5681801889732,
"count": 64663,
"self": 13.549240465261391,
"children": {
"process_trajectory": {
"total": 163.02262107680144,
"count": 64663,
"self": 162.17994571680902,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8426753599924268,
"count": 2,
"self": 0.8426753599924268
}
}
},
"_update_policy": {
"total": 263.99631864691037,
"count": 46,
"self": 147.70801077308715,
"children": {
"TorchPOCAOptimizer.update": {
"total": 116.28830787382321,
"count": 1383,
"self": 116.28830787382321
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.496992237865925e-06,
"count": 1,
"self": 2.496992237865925e-06
},
"TrainerController._save_models": {
"total": 0.3360714199952781,
"count": 1,
"self": 0.004281576999346726,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3317898429959314,
"count": 1,
"self": 0.3317898429959314
}
}
}
}
}
}
}