baseline / run_logs /timers.json
sinny's picture
baseline
cb33f3b
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.902220368385315,
"min": 1.8798245191574097,
"max": 3.2957026958465576,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 38896.6015625,
"min": 23470.833984375,
"max": 108659.1328125,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 55.61797752808989,
"min": 49.714285714285715,
"max": 999.0,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19800.0,
"min": 12324.0,
"max": 28844.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1501.7467793182816,
"min": 1199.5057223791089,
"max": 1540.44027129552,
"count": 492
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 267310.9267186541,
"min": 2401.634377486819,
"max": 299121.75718526833,
"count": 492
},
"SoccerTwos.Step.mean": {
"value": 4999978.0,
"min": 9440.0,
"max": 4999978.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 4999978.0,
"min": 9440.0,
"max": 4999978.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.019829465076327324,
"min": -0.09591928124427795,
"max": 0.21020308136940002,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 3.509815216064453,
"min": -14.855474472045898,
"max": 23.866817474365234,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.01356409676373005,
"min": -0.09563414007425308,
"max": 0.21305915713310242,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 2.4008450508117676,
"min": -15.107744216918945,
"max": 23.645427703857422,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.08759774057205114,
"min": -0.6153846153846154,
"max": 0.4061299994587898,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 15.504800081253052,
"min": -59.5175998210907,
"max": 49.892799854278564,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.08759774057205114,
"min": -0.6153846153846154,
"max": 0.4061299994587898,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 15.504800081253052,
"min": -59.5175998210907,
"max": 49.892799854278564,
"count": 500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.010770902594473834,
"min": 0.010770902594473834,
"max": 0.024406571467019,
"count": 241
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.010770902594473834,
"min": 0.010770902594473834,
"max": 0.024406571467019,
"count": 241
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10224802096684774,
"min": 6.370583942043595e-05,
"max": 0.10771091034015019,
"count": 241
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10224802096684774,
"min": 6.370583942043595e-05,
"max": 0.10771091034015019,
"count": 241
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.1042000745733579,
"min": 6.349220360183002e-05,
"max": 0.10975950236121813,
"count": 241
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.1042000745733579,
"min": 6.349220360183002e-05,
"max": 0.10975950236121813,
"count": 241
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 241
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 241
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 241
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 241
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 241
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 241
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676356153",
"python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]",
"command_line_arguments": "/home/olav/dev/anaconda3/envs/rl/bin/mlagents-learn baseline_config.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.x86_64 --run-id=baseline --no-graphics --results-dir=./ml-agents/results --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",
"numpy_version": "1.21.2",
"end_time_seconds": "1676360710"
},
"total": 4556.409521426001,
"count": 1,
"self": 0.21829356800299138,
"children": {
"run_training.setup": {
"total": 0.007075053999869851,
"count": 1,
"self": 0.007075053999869851
},
"TrainerController.start_learning": {
"total": 4556.184152803999,
"count": 1,
"self": 3.7660274021764053,
"children": {
"TrainerController._reset_env": {
"total": 2.7079156409854477,
"count": 25,
"self": 2.7079156409854477
},
"TrainerController.advance": {
"total": 4549.590081618844,
"count": 339195,
"self": 3.8062295802701556,
"children": {
"env_step": {
"total": 3325.751270890276,
"count": 339195,
"self": 2444.2383848079116,
"children": {
"SubprocessEnvManager._take_step": {
"total": 879.2354413706198,
"count": 339195,
"self": 24.615664796565397,
"children": {
"TorchPolicy.evaluate": {
"total": 854.6197765740544,
"count": 630046,
"self": 854.6197765740544
}
}
},
"workers": {
"total": 2.277444711744465,
"count": 339195,
"self": 0.0,
"children": {
"worker_root": {
"total": 4550.621719077015,
"count": 339195,
"is_parallel": true,
"self": 2565.3810402612326,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018831889974535443,
"count": 2,
"is_parallel": true,
"self": 0.00047415399967576377,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014090349977777805,
"count": 8,
"is_parallel": true,
"self": 0.0014090349977777805
}
}
},
"UnityEnvironment.step": {
"total": 0.014492382997559616,
"count": 1,
"is_parallel": true,
"self": 0.00042730500354082324,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003527939988998696,
"count": 1,
"is_parallel": true,
"self": 0.0003527939988998696
},
"communicator.exchange": {
"total": 0.012379479998344323,
"count": 1,
"is_parallel": true,
"self": 0.012379479998344323
},
"steps_from_proto": {
"total": 0.0013328039967746008,
"count": 2,
"is_parallel": true,
"self": 0.00026445299954502843,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010683509972295724,
"count": 8,
"is_parallel": true,
"self": 0.0010683509972295724
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1985.2043392907872,
"count": 339194,
"is_parallel": true,
"self": 135.7385649650896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.14345474129004,
"count": 339194,
"is_parallel": true,
"self": 91.14345474129004
},
"communicator.exchange": {
"total": 1352.4512743431078,
"count": 339194,
"is_parallel": true,
"self": 1352.4512743431078
},
"steps_from_proto": {
"total": 405.8710452412997,
"count": 678388,
"is_parallel": true,
"self": 76.04295478028507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 329.82809046101465,
"count": 2713552,
"is_parallel": true,
"self": 329.82809046101465
}
}
}
}
},
"steps_from_proto": {
"total": 0.03633952499512816,
"count": 48,
"is_parallel": true,
"self": 0.006832120940089226,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.029507404055038933,
"count": 192,
"is_parallel": true,
"self": 0.029507404055038933
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1220.032581148298,
"count": 339195,
"self": 31.443536122798832,
"children": {
"process_trajectory": {
"total": 454.6751856874653,
"count": 339195,
"self": 453.46062648547013,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2145592019951437,
"count": 10,
"self": 1.2145592019951437
}
}
},
"_update_policy": {
"total": 733.913859338034,
"count": 241,
"self": 519.5579340195,
"children": {
"TorchPOCAOptimizer.update": {
"total": 214.355925318534,
"count": 7233,
"self": 214.355925318534
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.899936124682426e-07,
"count": 1,
"self": 6.899936124682426e-07
},
"TrainerController._save_models": {
"total": 0.12012745199899655,
"count": 1,
"self": 0.0008023029949981719,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11932514900399838,
"count": 1,
"self": 0.11932514900399838
}
}
}
}
}
}
}