poca-SoccerTwos / run_logs /timers.json
Terps's picture
First Push
0cb907a
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.5969356298446655,
"min": 1.5406135320663452,
"max": 3.2957420349121094,
"count": 1000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 32807.4453125,
"min": 22233.03515625,
"max": 119406.3984375,
"count": 1000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 52.81720430107527,
"min": 40.56198347107438,
"max": 999.0,
"count": 1000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19648.0,
"min": 14076.0,
"max": 23844.0,
"count": 1000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1555.4992597326595,
"min": 1190.120050817967,
"max": 1604.2552553318303,
"count": 992
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 289322.8623102747,
"min": 2394.009544151198,
"max": 379028.06362600107,
"count": 992
},
"SoccerTwos.Step.mean": {
"value": 9999972.0,
"min": 9174.0,
"max": 9999972.0,
"count": 1000
},
"SoccerTwos.Step.sum": {
"value": 9999972.0,
"min": 9174.0,
"max": 9999972.0,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.014413188211619854,
"min": -0.12347006052732468,
"max": 0.12490702420473099,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -2.6664397716522217,
"min": -24.955711364746094,
"max": 17.15989875793457,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.010898062027990818,
"min": -0.12485354393720627,
"max": 0.12470623850822449,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.016141414642334,
"min": -24.727825164794922,
"max": 16.87221908569336,
"count": 1000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.13524540566109322,
"min": -0.5605333337077388,
"max": 0.41887500137090683,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 25.020400047302246,
"min": -56.325600147247314,
"max": 54.54360020160675,
"count": 1000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.13524540566109322,
"min": -0.5605333337077388,
"max": 0.41887500137090683,
"count": 1000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 25.020400047302246,
"min": -56.325600147247314,
"max": 54.54360020160675,
"count": 1000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.02141846805801227,
"min": 0.010343785071745515,
"max": 0.02435030248016119,
"count": 482
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.02141846805801227,
"min": 0.010343785071745515,
"max": 0.02435030248016119,
"count": 482
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10125019202629724,
"min": 0.00030965355545049534,
"max": 0.12248869289954503,
"count": 482
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10125019202629724,
"min": 0.00030965355545049534,
"max": 0.12248869289954503,
"count": 482
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10259012083212535,
"min": 0.00030871983423518635,
"max": 0.12475258807341258,
"count": 482
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10259012083212535,
"min": 0.00030871983423518635,
"max": 0.12475258807341258,
"count": 482
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 482
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 482
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 482
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 482
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 482
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 482
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1694708790",
"python_version": "3.9.18 | packaged by conda-forge | (main, Aug 30 2023, 03:49:32) \n[GCC 12.3.0]",
"command_line_arguments": "/home/terps/mambaforge/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694736508"
},
"total": 27718.452107893998,
"count": 1,
"self": 1.7995216749986866,
"children": {
"run_training.setup": {
"total": 0.012232699999003671,
"count": 1,
"self": 0.012232699999003671
},
"TrainerController.start_learning": {
"total": 27716.640353519,
"count": 1,
"self": 19.2576742155361,
"children": {
"TrainerController._reset_env": {
"total": 8.84835274298166,
"count": 21,
"self": 8.84835274298166
},
"TrainerController.advance": {
"total": 27688.247795048483,
"count": 680429,
"self": 19.05893027050115,
"children": {
"env_step": {
"total": 22157.30852160375,
"count": 680429,
"self": 15638.15256235451,
"children": {
"SubprocessEnvManager._take_step": {
"total": 6507.746948996195,
"count": 680429,
"self": 113.61552996908722,
"children": {
"TorchPolicy.evaluate": {
"total": 6394.131419027108,
"count": 1254764,
"self": 6394.131419027108
}
}
},
"workers": {
"total": 11.40901025304629,
"count": 680428,
"self": 0.0,
"children": {
"worker_root": {
"total": 27672.763382924164,
"count": 680428,
"is_parallel": true,
"self": 14029.47554577728,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007280599998921389,
"count": 2,
"is_parallel": true,
"self": 0.005340200004866347,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001940399994055042,
"count": 8,
"is_parallel": true,
"self": 0.001940399994055042
}
}
},
"UnityEnvironment.step": {
"total": 0.03416270000161603,
"count": 1,
"is_parallel": true,
"self": 0.0006320999964373186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005296000017551705,
"count": 1,
"is_parallel": true,
"self": 0.0005296000017551705
},
"communicator.exchange": {
"total": 0.031072600002516992,
"count": 1,
"is_parallel": true,
"self": 0.031072600002516992
},
"steps_from_proto": {
"total": 0.0019284000009065494,
"count": 2,
"is_parallel": true,
"self": 0.00048099999912665226,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014474000017798971,
"count": 8,
"is_parallel": true,
"self": 0.0014474000017798971
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 13643.25105359788,
"count": 680427,
"is_parallel": true,
"self": 402.79831428049874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 276.44210654751805,
"count": 680427,
"is_parallel": true,
"self": 276.44210654751805
},
"communicator.exchange": {
"total": 11742.215522667906,
"count": 680427,
"is_parallel": true,
"self": 11742.215522667906
},
"steps_from_proto": {
"total": 1221.795110101957,
"count": 1360854,
"is_parallel": true,
"self": 273.6090259386874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 948.1860841632697,
"count": 5443416,
"is_parallel": true,
"self": 948.1860841632697
}
}
}
}
},
"steps_from_proto": {
"total": 0.03678354900330305,
"count": 40,
"is_parallel": true,
"self": 0.008402747000218369,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.028380802003084682,
"count": 160,
"is_parallel": true,
"self": 0.028380802003084682
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 5511.880343174231,
"count": 680428,
"self": 128.80195408420332,
"children": {
"process_trajectory": {
"total": 2575.0881813440137,
"count": 680428,
"self": 2568.601877004996,
"children": {
"RLTrainer._checkpoint": {
"total": 6.486304339017806,
"count": 20,
"self": 6.486304339017806
}
}
},
"_update_policy": {
"total": 2807.9902077460138,
"count": 483,
"self": 1697.4578579989175,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1110.5323497470963,
"count": 14490,
"self": 1110.5323497470963
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5999976312741637e-06,
"count": 1,
"self": 1.5999976312741637e-06
},
"TrainerController._save_models": {
"total": 0.28652991200215183,
"count": 1,
"self": 0.002179615003115032,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2843502969990368,
"count": 1,
"self": 0.2843502969990368
}
}
}
}
}
}
}