poca-SoccerTwos / run_logs /timers.json
thomaspalomares's picture
Second Push
56325d9 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.215240478515625,
"min": 3.2082087993621826,
"max": 3.2788138389587402,
"count": 30
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 58440.2109375,
"min": 6609.21240234375,
"max": 112997.453125,
"count": 30
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 852.5,
"min": 372.2307692307692,
"max": 999.0,
"count": 30
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 20460.0,
"min": 6204.0,
"max": 31716.0,
"count": 30
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1212.351426911121,
"min": 1201.9235520535651,
"max": 1214.940296813811,
"count": 29
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 4849.405707644484,
"min": 2403.8471041071302,
"max": 16987.397148141066,
"count": 29
},
"SoccerTwos.Step.mean": {
"value": 339854.0,
"min": 49378.0,
"max": 339854.0,
"count": 30
},
"SoccerTwos.Step.sum": {
"value": 339854.0,
"min": 49378.0,
"max": 339854.0,
"count": 30
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.006578196305781603,
"min": 0.006578196305781603,
"max": 0.06802091002464294,
"count": 30
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.07893835753202438,
"min": 0.07893835753202438,
"max": 1.088334560394287,
"count": 30
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.004074022639542818,
"min": 0.004074022639542818,
"max": 0.06785643100738525,
"count": 30
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.048888273537158966,
"min": 0.048888273537158966,
"max": 1.085702896118164,
"count": 30
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 30
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 30
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.3333333333333333,
"min": -0.3333333333333333,
"max": 0.2857894771977475,
"count": 30
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -4.0,
"min": -4.0,
"max": 5.430000066757202,
"count": 30
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.3333333333333333,
"min": -0.3333333333333333,
"max": 0.2857894771977475,
"count": 30
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -4.0,
"min": -4.0,
"max": 5.430000066757202,
"count": 30
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.016774885818207016,
"min": 0.013413160684285686,
"max": 0.020140104663247862,
"count": 13
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.016774885818207016,
"min": 0.013413160684285686,
"max": 0.020140104663247862,
"count": 13
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0025689200653384128,
"min": 0.0003981584195571486,
"max": 0.005156840841906766,
"count": 13
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0025689200653384128,
"min": 0.0003981584195571486,
"max": 0.005156840841906766,
"count": 13
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0025834310023734965,
"min": 0.0003941108460518687,
"max": 0.005347981389301519,
"count": 13
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0025834310023734965,
"min": 0.0003941108460518687,
"max": 0.005347981389301519,
"count": 13
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 13
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 13
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.19999999999999996,
"max": 0.20000000000000007,
"count": 13
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.19999999999999996,
"max": 0.20000000000000007,
"count": 13
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 13
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 13
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1721744065",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/thopalomares/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721745921"
},
"total": 1856.0187186140001,
"count": 1,
"self": 0.3318577139998524,
"children": {
"run_training.setup": {
"total": 0.01629420300014317,
"count": 1,
"self": 0.01629420300014317
},
"TrainerController.start_learning": {
"total": 1855.6705666970001,
"count": 1,
"self": 0.770913486050631,
"children": {
"TrainerController._reset_env": {
"total": 1.815844243000356,
"count": 2,
"self": 1.815844243000356
},
"TrainerController.advance": {
"total": 1852.6214321879493,
"count": 20285,
"self": 0.9898066918790391,
"children": {
"env_step": {
"total": 1171.8839023150204,
"count": 20285,
"self": 1031.3447389960074,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.9729437979954,
"count": 20285,
"self": 6.600656839059866,
"children": {
"TorchPolicy.evaluate": {
"total": 133.37228695893555,
"count": 40268,
"self": 133.37228695893555
}
}
},
"workers": {
"total": 0.5662195210175014,
"count": 20284,
"self": 0.0,
"children": {
"worker_root": {
"total": 1853.3329737060058,
"count": 20284,
"is_parallel": true,
"self": 927.5884458780147,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0047305030002462445,
"count": 2,
"is_parallel": true,
"self": 0.0011434060006649815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003587096999581263,
"count": 8,
"is_parallel": true,
"self": 0.003587096999581263
}
}
},
"UnityEnvironment.step": {
"total": 0.04282491300000402,
"count": 1,
"is_parallel": true,
"self": 0.0008339199998772528,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005496940002558404,
"count": 1,
"is_parallel": true,
"self": 0.0005496940002558404
},
"communicator.exchange": {
"total": 0.03921005099982722,
"count": 1,
"is_parallel": true,
"self": 0.03921005099982722
},
"steps_from_proto": {
"total": 0.0022312480000437063,
"count": 2,
"is_parallel": true,
"self": 0.0004841500003749388,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017470979996687674,
"count": 8,
"is_parallel": true,
"self": 0.0017470979996687674
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 925.741009410991,
"count": 20283,
"is_parallel": true,
"self": 21.56576160804525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 18.77643948494233,
"count": 20283,
"is_parallel": true,
"self": 18.77643948494233
},
"communicator.exchange": {
"total": 822.8149252780249,
"count": 20283,
"is_parallel": true,
"self": 822.8149252780249
},
"steps_from_proto": {
"total": 62.583883039978446,
"count": 40566,
"is_parallel": true,
"self": 13.445873751940326,
"children": {
"_process_rank_one_or_two_observation": {
"total": 49.13800928803812,
"count": 162264,
"is_parallel": true,
"self": 49.13800928803812
}
}
}
}
},
"steps_from_proto": {
"total": 0.0035184170001230086,
"count": 2,
"is_parallel": true,
"self": 0.0007879720010350866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002730444999087922,
"count": 8,
"is_parallel": true,
"self": 0.002730444999087922
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 679.7477231810499,
"count": 20284,
"self": 6.3452692170303635,
"children": {
"process_trajectory": {
"total": 88.60656461601957,
"count": 20284,
"self": 88.60656461601957
},
"_update_policy": {
"total": 584.795889348,
"count": 13,
"self": 53.833978601001036,
"children": {
"TorchPOCAOptimizer.update": {
"total": 530.9619107469989,
"count": 402,
"self": 530.9619107469989
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.9960002646257635e-06,
"count": 1,
"self": 1.9960002646257635e-06
},
"TrainerController._save_models": {
"total": 0.4623747839996213,
"count": 1,
"self": 0.023142872999414976,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4392319110002063,
"count": 1,
"self": 0.4392319110002063
}
}
}
}
}
}
}