{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8620750904083252, "min": 1.7322965860366821, "max": 3.2957098484039307, "count": 800 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37956.5390625, "min": 10136.2109375, "max": 131013.046875, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.78350515463917, "min": 41.1271186440678, "max": 999.0, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19704.0, "min": 15624.0, "max": 26332.0, "count": 800 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1517.8703778096872, "min": 1191.3111912471961, "max": 1584.5306654815859, "count": 797 }, "SoccerTwos.Self-play.ELO.sum": { "value": 294466.8532950793, "min": 2385.854522756917, "max": 356743.21496192773, "count": 797 }, "SoccerTwos.Step.mean": { "value": 7999986.0, "min": 9772.0, "max": 7999986.0, "count": 800 }, "SoccerTwos.Step.sum": { "value": 7999986.0, "min": 9772.0, "max": 7999986.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.019200840964913368, "min": -0.12389080971479416, "max": 0.1440913826227188, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.744163990020752, "min": -19.698638916015625, "max": 22.332225799560547, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01900632679462433, "min": -0.12310798466205597, "max": 0.14770977199077606, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.7062337398529053, "min": -19.574169158935547, "max": 22.73837661743164, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07777640941815499, "min": -0.6819374999031425, "max": 0.4021428589309965, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.166399836540222, "min": -61.93959987163544, "max": 44.75040006637573, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07777640941815499, "min": -0.6819374999031425, "max": 0.4021428589309965, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.166399836540222, "min": -61.93959987163544, "max": 44.75040006637573, "count": 800 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012417273254444201, "min": 0.010295493935700506, "max": 0.026601607150708636, "count": 386 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012417273254444201, "min": 0.010295493935700506, "max": 0.026601607150708636, "count": 386 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11116273924708367, "min": 0.0003609630982585562, "max": 0.12107628559072812, "count": 386 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11116273924708367, "min": 0.0003609630982585562, "max": 0.12107628559072812, "count": 386 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11284758771459262, "min": 0.0003731070801829143, "max": 0.1231194314857324, "count": 386 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11284758771459262, "min": 0.0003731070801829143, "max": 0.1231194314857324, "count": 386 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 386 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 386 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 386 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 386 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 386 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 386 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715614057", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/opt/conda/bin/mlagents-learn /kaggle/input/soccertwosmod-yaml/SoccerTwosMod.yaml --env=/kaggle/working/ml-agents/training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1715651658" }, "total": 37601.068734141, "count": 1, "self": 0.4296618430016679, "children": { "run_training.setup": { "total": 0.11653860799998483, "count": 1, "self": 0.11653860799998483 }, "TrainerController.start_learning": { "total": 37600.52253369, "count": 1, "self": 19.85771098830446, "children": { "TrainerController._reset_env": { "total": 3.9743024930051547, "count": 40, "self": 3.9743024930051547 }, "TrainerController.advance": { "total": 37576.42886269968, "count": 547736, "self": 21.379173465371423, "children": { "env_step": { "total": 16214.532469752776, "count": 547736, "self": 13285.727275800433, "children": { "SubprocessEnvManager._take_step": { "total": 2915.6621348028348, "count": 547736, "self": 116.82275330984066, "children": { "TorchPolicy.evaluate": { "total": 2798.839381492994, "count": 1007690, "self": 2798.839381492994 } } }, "workers": { "total": 13.143059149509327, "count": 547736, "self": 0.0, "children": { "worker_root": { "total": 37562.83136124097, "count": 547736, "is_parallel": true, "self": 27048.060822832686, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00414497899998878, "count": 2, "is_parallel": true, "self": 0.0009311310000725825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032138479999161973, "count": 8, "is_parallel": true, "self": 0.0032138479999161973 } } }, "UnityEnvironment.step": { "total": 0.03975850299997319, "count": 1, "is_parallel": true, "self": 0.0014542309999114877, "children": { "UnityEnvironment._generate_step_input": { "total": 0.001016445000004751, "count": 1, "is_parallel": true, "self": 0.001016445000004751 }, "communicator.exchange": { "total": 0.032271460000004026, "count": 1, "is_parallel": true, "self": 0.032271460000004026 }, "steps_from_proto": { "total": 0.005016367000052924, "count": 2, "is_parallel": true, "self": 0.0008724719999690933, "children": { "_process_rank_one_or_two_observation": { "total": 0.00414389500008383, "count": 8, "is_parallel": true, "self": 0.00414389500008383 } } } } } } }, "UnityEnvironment.step": { "total": 10514.644604633297, "count": 547735, "is_parallel": true, "self": 635.2627661991974, "children": { "UnityEnvironment._generate_step_input": { "total": 505.036169147941, "count": 547735, "is_parallel": true, "self": 505.036169147941 }, "communicator.exchange": { "total": 7205.633974305054, "count": 547735, "is_parallel": true, "self": 7205.633974305054 }, "steps_from_proto": { "total": 2168.7116949811048, "count": 1095470, "is_parallel": true, "self": 367.403915294944, "children": { "_process_rank_one_or_two_observation": { "total": 1801.3077796861608, "count": 4381880, "is_parallel": true, "self": 1801.3077796861608 } } } } }, "steps_from_proto": { "total": 0.12593377498637892, "count": 78, "is_parallel": true, "self": 0.022071329991604216, "children": { "_process_rank_one_or_two_observation": { "total": 0.1038624449947747, "count": 312, "is_parallel": true, "self": 0.1038624449947747 } } } } } } } } }, "trainer_advance": { "total": 21340.517219481528, "count": 547736, "self": 144.2386461867427, "children": { "process_trajectory": { "total": 3291.191148722807, "count": 547736, "self": 3287.161968706807, "children": { "RLTrainer._checkpoint": { "total": 4.029180016000282, "count": 16, "self": 4.029180016000282 } } }, "_update_policy": { "total": 17905.08742457198, "count": 386, "self": 2443.187175448111, "children": { "TorchPOCAOptimizer.update": { "total": 15461.900249123868, "count": 11580, "self": 15461.900249123868 } } } } } } }, "trainer_threads": { "total": 1.3950048014521599e-06, "count": 1, "self": 1.3950048014521599e-06 }, "TrainerController._save_models": { "total": 0.26165611400210764, "count": 1, "self": 0.004365993998362683, "children": { "RLTrainer._checkpoint": { "total": 0.25729012000374496, "count": 1, "self": 0.25729012000374496 } } } } } } }