poca-SoccerTwos / run_logs /timers.json
monti-python's picture
First training for SoccerTwos
9bea408 verified
raw
history blame
20.1 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.127368927001953,
"min": 3.0976717472076416,
"max": 3.189692735671997,
"count": 242
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 100075.8046875,
"min": 15248.029296875,
"max": 130752.9921875,
"count": 242
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 602.75,
"min": 428.6,
"max": 999.0,
"count": 242
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19288.0,
"min": 12792.0,
"max": 27500.0,
"count": 242
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1206.8610828455319,
"min": 1186.7395702703918,
"max": 1212.688940503701,
"count": 171
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 2413.7221656910638,
"min": 2374.981983800177,
"max": 14285.838900584944,
"count": 171
},
"SoccerTwos.Step.mean": {
"value": 7419648.0,
"min": 5009269.0,
"max": 7419648.0,
"count": 242
},
"SoccerTwos.Step.sum": {
"value": 7419648.0,
"min": 5009269.0,
"max": 7419648.0,
"count": 242
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0008507742313668132,
"min": -0.023815060034394264,
"max": 0.007759155239909887,
"count": 242
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.013612387701869011,
"min": -0.26196566224098206,
"max": 0.102737195789814,
"count": 242
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.0008724190993234515,
"min": -0.024355709552764893,
"max": 0.007041024509817362,
"count": 242
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.013958705589175224,
"min": -0.2679128050804138,
"max": 0.08854017406702042,
"count": 242
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 242
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 242
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.0,
"min": -0.5,
"max": 0.25085714033671785,
"count": 242
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 0.0,
"min": -6.0,
"max": 4.1572000831365585,
"count": 242
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.0,
"min": -0.5,
"max": 0.25085714033671785,
"count": 242
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 0.0,
"min": -6.0,
"max": 4.1572000831365585,
"count": 242
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 242
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 242
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.017036540707340463,
"min": 0.01092280437393735,
"max": 0.022488900188667078,
"count": 112
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.017036540707340463,
"min": 0.01092280437393735,
"max": 0.022488900188667078,
"count": 112
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 2.7369898816687055e-05,
"min": 1.643655115420491e-07,
"max": 0.004814238233181337,
"count": 112
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 2.7369898816687055e-05,
"min": 1.643655115420491e-07,
"max": 0.004814238233181337,
"count": 112
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 2.73141261307804e-05,
"min": 1.5780971776753934e-07,
"max": 0.004814112830596666,
"count": 112
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 2.73141261307804e-05,
"min": 1.5780971776753934e-07,
"max": 0.004814112830596666,
"count": 112
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 112
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 112
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 112
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 112
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 112
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 112
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1724497816",
"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": "1724503464"
},
"total": 5648.517334780001,
"count": 1,
"self": 0.27658308199897874,
"children": {
"run_training.setup": {
"total": 0.0332001950009726,
"count": 1,
"self": 0.0332001950009726
},
"TrainerController.start_learning": {
"total": 5648.207551503001,
"count": 1,
"self": 3.444035428852658,
"children": {
"TrainerController._reset_env": {
"total": 5.419610770026338,
"count": 14,
"self": 5.419610770026338
},
"TrainerController.advance": {
"total": 5639.084447214118,
"count": 157405,
"self": 3.953651600939338,
"children": {
"env_step": {
"total": 4591.684293982689,
"count": 157405,
"self": 2794.746072800728,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1794.5164113909996,
"count": 157405,
"self": 30.40238449710887,
"children": {
"TorchPolicy.evaluate": {
"total": 1764.1140268938907,
"count": 312540,
"self": 1764.1140268938907
}
}
},
"workers": {
"total": 2.421809790961561,
"count": 157404,
"self": 0.0,
"children": {
"worker_root": {
"total": 5640.890048837231,
"count": 157404,
"is_parallel": true,
"self": 3259.729416945236,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003890229985699989,
"count": 2,
"is_parallel": true,
"self": 0.0014303580101113766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024598719755886123,
"count": 8,
"is_parallel": true,
"self": 0.0024598719755886123
}
}
},
"UnityEnvironment.step": {
"total": 0.03318805700109806,
"count": 1,
"is_parallel": true,
"self": 0.0006699319928884506,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004741019947687164,
"count": 1,
"is_parallel": true,
"self": 0.0004741019947687164
},
"communicator.exchange": {
"total": 0.029174192997743376,
"count": 1,
"is_parallel": true,
"self": 0.029174192997743376
},
"steps_from_proto": {
"total": 0.0028698300156975165,
"count": 2,
"is_parallel": true,
"self": 0.0007267300534294918,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021430999622680247,
"count": 8,
"is_parallel": true,
"self": 0.0021430999622680247
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.019987581021268852,
"count": 26,
"is_parallel": true,
"self": 0.004352420073701069,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.015635160947567783,
"count": 104,
"is_parallel": true,
"self": 0.015635160947567783
}
}
},
"UnityEnvironment.step": {
"total": 2381.1406443109736,
"count": 157403,
"is_parallel": true,
"self": 77.82742763230635,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 50.70297598854813,
"count": 157403,
"is_parallel": true,
"self": 50.70297598854813
},
"communicator.exchange": {
"total": 2001.539421746449,
"count": 157403,
"is_parallel": true,
"self": 2001.539421746449
},
"steps_from_proto": {
"total": 251.07081894367002,
"count": 314806,
"is_parallel": true,
"self": 54.14723351367866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 196.92358542999136,
"count": 1259224,
"is_parallel": true,
"self": 196.92358542999136
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1043.4465016304894,
"count": 157404,
"self": 32.840051461957046,
"children": {
"process_trajectory": {
"total": 388.42192564149445,
"count": 157404,
"self": 386.8210518114938,
"children": {
"RLTrainer._checkpoint": {
"total": 1.600873830000637,
"count": 4,
"self": 1.600873830000637
}
}
},
"_update_policy": {
"total": 622.1845245270379,
"count": 112,
"self": 343.7758908315009,
"children": {
"TorchPOCAOptimizer.update": {
"total": 278.408633695537,
"count": 3369,
"self": 278.408633695537
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1130032362416387e-06,
"count": 1,
"self": 1.1130032362416387e-06
},
"TrainerController._save_models": {
"total": 0.2594569770008093,
"count": 1,
"self": 0.004013034005765803,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25544394299504347,
"count": 1,
"self": 0.25544394299504347
}
}
}
}
}
}
}