poca-SoccerTwos / run_logs /timers.json
dcarpintero's picture
First Push
ea94fed
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.081484794616699,
"min": 3.059194803237915,
"max": 3.2957420349121094,
"count": 170
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 41809.5859375,
"min": 20376.7734375,
"max": 119950.765625,
"count": 170
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 623.375,
"min": 264.89473684210526,
"max": 999.0,
"count": 170
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19948.0,
"min": 16420.0,
"max": 25452.0,
"count": 170
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1226.5894243205837,
"min": 1198.3441547872985,
"max": 1230.5858911431674,
"count": 157
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 17172.25194048817,
"min": 2399.932465579107,
"max": 46667.30349447222,
"count": 157
},
"SoccerTwos.Step.mean": {
"value": 1699439.0,
"min": 9476.0,
"max": 1699439.0,
"count": 170
},
"SoccerTwos.Step.sum": {
"value": 1699439.0,
"min": 9476.0,
"max": 1699439.0,
"count": 170
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0047509875148534775,
"min": -0.03272517770528793,
"max": 0.0965859666466713,
"count": 170
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.07601580023765564,
"min": -0.7096143960952759,
"max": 1.434480905532837,
"count": 170
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.007963282987475395,
"min": -0.03359228000044823,
"max": 0.0965752825140953,
"count": 170
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.12741252779960632,
"min": -0.8014217019081116,
"max": 1.255362629890442,
"count": 170
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 170
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 170
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.060837503522634506,
"min": -0.7566999992863699,
"max": 0.4302727254954251,
"count": 170
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -0.9734000563621521,
"min": -16.647399984300137,
"max": 9.465999960899353,
"count": 170
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.060837503522634506,
"min": -0.7566999992863699,
"max": 0.4302727254954251,
"count": 170
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -0.9734000563621521,
"min": -16.647399984300137,
"max": 9.465999960899353,
"count": 170
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 170
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 170
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01648376785451546,
"min": 0.010964773986294555,
"max": 0.02255034991831053,
"count": 79
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01648376785451546,
"min": 0.010964773986294555,
"max": 0.02255034991831053,
"count": 79
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.00882468478133281,
"min": 0.00010951824757891397,
"max": 0.01712936091547211,
"count": 79
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.00882468478133281,
"min": 0.00010951824757891397,
"max": 0.01712936091547211,
"count": 79
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.008880139126752814,
"min": 0.00010706242319429294,
"max": 0.018025920043389,
"count": 79
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.008880139126752814,
"min": 0.00010706242319429294,
"max": 0.018025920043389,
"count": 79
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 79
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 79
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 79
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 79
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 79
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 79
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688557029",
"python_version": "3.9.16 (main, May 15 2023, 18:51:40) \n[Clang 14.0.6 ]",
"command_line_arguments": "/Users/diego/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos-v2 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0",
"numpy_version": "1.21.2",
"end_time_seconds": "1688566447"
},
"total": 9417.789399227,
"count": 1,
"self": 0.3454384579999896,
"children": {
"run_training.setup": {
"total": 0.09507552799999974,
"count": 1,
"self": 0.09507552799999974
},
"TrainerController.start_learning": {
"total": 9417.348885241001,
"count": 1,
"self": 3.6462328950347,
"children": {
"TrainerController._reset_env": {
"total": 6.608537207000312,
"count": 9,
"self": 6.608537207000312
},
"TrainerController.advance": {
"total": 9406.798419319966,
"count": 110216,
"self": 4.197785997124811,
"children": {
"env_step": {
"total": 2790.417352023997,
"count": 110216,
"self": 2288.309696617711,
"children": {
"SubprocessEnvManager._take_step": {
"total": 499.5822412721519,
"count": 110216,
"self": 23.297527914851344,
"children": {
"TorchPolicy.evaluate": {
"total": 476.2847133573006,
"count": 218438,
"self": 476.2847133573006
}
}
},
"workers": {
"total": 2.5254141341341523,
"count": 110215,
"self": 0.0,
"children": {
"worker_root": {
"total": 9404.374303185034,
"count": 110215,
"is_parallel": true,
"self": 7545.341368127849,
"children": {
"steps_from_proto": {
"total": 0.02201048999678168,
"count": 18,
"is_parallel": true,
"self": 0.004358723992541336,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.017651766004240343,
"count": 72,
"is_parallel": true,
"self": 0.017651766004240343
}
}
},
"UnityEnvironment.step": {
"total": 1859.0109245671874,
"count": 110215,
"is_parallel": true,
"self": 100.0206033539896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 59.51049099902872,
"count": 110215,
"is_parallel": true,
"self": 59.51049099902872
},
"communicator.exchange": {
"total": 1395.731036199136,
"count": 110215,
"is_parallel": true,
"self": 1395.731036199136
},
"steps_from_proto": {
"total": 303.7487940150331,
"count": 220430,
"is_parallel": true,
"self": 63.59694605153743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 240.1518479634957,
"count": 881720,
"is_parallel": true,
"self": 240.1518479634957
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 6612.183281298845,
"count": 110215,
"self": 22.764543413787578,
"children": {
"process_trajectory": {
"total": 680.3184287390568,
"count": 110215,
"self": 679.2925268510567,
"children": {
"RLTrainer._checkpoint": {
"total": 1.025901888000135,
"count": 3,
"self": 1.025901888000135
}
}
},
"_update_policy": {
"total": 5909.100309146001,
"count": 79,
"self": 388.98209618901365,
"children": {
"TorchPOCAOptimizer.update": {
"total": 5520.118212956987,
"count": 2370,
"self": 5520.118212956987
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.65599885804113e-06,
"count": 1,
"self": 1.65599885804113e-06
},
"TrainerController._save_models": {
"total": 0.2956941630000074,
"count": 1,
"self": 0.0027811210002255393,
"children": {
"RLTrainer._checkpoint": {
"total": 0.29291304199978185,
"count": 1,
"self": 0.29291304199978185
}
}
}
}
}
}
}