{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5712438821792603, "min": 1.5587527751922607, "max": 2.0243117809295654, "count": 308 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34894.18359375, "min": 27434.048828125, "max": 45251.359375, "count": 308 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.888888888888886, "min": 42.02654867256637, "max": 84.96551724137932, "count": 308 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20840.0, "min": 17400.0, "max": 21824.0, "count": 308 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1264.454923827002, "min": 1173.1927203833575, "max": 1292.2790965101735, "count": 308 }, "SoccerTwos.Self-play.ELO.sum": { "value": 227601.88628886035, "min": 146698.67756814498, "max": 274048.9838696183, "count": 308 }, "SoccerTwos.Step.mean": { "value": 3079958.0, "min": 9870.0, "max": 3079958.0, "count": 308 }, "SoccerTwos.Step.sum": { "value": 3079958.0, "min": 9870.0, "max": 3079958.0, "count": 308 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017327221110463142, "min": -0.11203747242689133, "max": 0.10505310446023941, "count": 308 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.1188998222351074, "min": -19.606557846069336, "max": 20.275249481201172, "count": 308 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.014008126221597195, "min": -0.11430858075618744, "max": 0.11353336274623871, "count": 308 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.5214626789093018, "min": -20.00400161743164, "max": 21.91193962097168, "count": 308 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 308 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 308 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11526444554328918, "min": -0.29855857193470003, "max": 0.315018183655209, "count": 308 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.747600197792053, "min": -50.76240026950836, "max": 62.373600363731384, "count": 308 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11526444554328918, "min": -0.29855857193470003, "max": 0.315018183655209, "count": 308 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.747600197792053, "min": -50.76240026950836, "max": 62.373600363731384, "count": 308 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 308 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 308 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014509687471824387, "min": 0.011130414668393011, "max": 0.021387927453118512, "count": 149 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014509687471824387, "min": 0.011130414668393011, "max": 0.021387927453118512, "count": 149 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10417577028274536, "min": 0.08628185093402863, "max": 0.12103650743762652, "count": 149 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10417577028274536, "min": 0.08628185093402863, "max": 0.12103650743762652, "count": 149 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10661319221059481, "min": 0.08823907102147738, "max": 0.12421340743700664, "count": 149 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10661319221059481, "min": 0.08823907102147738, "max": 0.12421340743700664, "count": 149 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 149 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 149 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 149 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 149 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 149 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 149 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712852912", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos_7 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712860334" }, "total": 7422.35113601, "count": 1, "self": 4.956130135000421, "children": { "run_training.setup": { "total": 0.06972608000000946, "count": 1, "self": 0.06972608000000946 }, "TrainerController.start_learning": { "total": 7417.325279795, "count": 1, "self": 5.4442507271742215, "children": { "TrainerController._reset_env": { "total": 29.171038249998958, "count": 16, "self": 29.171038249998958 }, "TrainerController.advance": { "total": 7382.708459428827, "count": 214518, "self": 5.693532849913026, "children": { "env_step": { "total": 5708.206104742876, "count": 214518, "self": 4394.0394083652955, "children": { "SubprocessEnvManager._take_step": { "total": 1310.9314957215418, "count": 214518, "self": 35.09114510350105, "children": { "TorchPolicy.evaluate": { "total": 1275.8403506180407, "count": 387544, "self": 1275.8403506180407 } } }, "workers": { "total": 3.2352006560385576, "count": 214517, "self": 0.0, "children": { "worker_root": { "total": 7401.50360033186, "count": 214517, "is_parallel": true, "self": 3711.771301610851, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006357496999953582, "count": 2, "is_parallel": true, "self": 0.003800963999879059, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025565330000745234, "count": 8, "is_parallel": true, "self": 0.0025565330000745234 } } }, "UnityEnvironment.step": { "total": 0.04533018199998651, "count": 1, "is_parallel": true, "self": 0.0012176590000194665, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008767979999788622, "count": 1, "is_parallel": true, "self": 0.0008767979999788622 }, "communicator.exchange": { "total": 0.03945899199999303, "count": 1, "is_parallel": true, "self": 0.03945899199999303 }, "steps_from_proto": { "total": 0.003776732999995147, "count": 2, "is_parallel": true, "self": 0.0007150210000190782, "children": { "_process_rank_one_or_two_observation": { "total": 0.003061711999976069, "count": 8, "is_parallel": true, "self": 0.003061711999976069 } } } } } } }, "UnityEnvironment.step": { "total": 3689.69585746801, "count": 214516, "is_parallel": true, "self": 224.85616908131578, "children": { "UnityEnvironment._generate_step_input": { "total": 154.20964920780523, "count": 214516, "is_parallel": true, "self": 154.20964920780523 }, "communicator.exchange": { "total": 2578.6190841460702, "count": 214516, "is_parallel": true, "self": 2578.6190841460702 }, "steps_from_proto": { "total": 732.0109550328189, "count": 429032, "is_parallel": true, "self": 124.626059117973, "children": { "_process_rank_one_or_two_observation": { "total": 607.3848959148459, "count": 1716128, "is_parallel": true, "self": 607.3848959148459 } } } } }, "steps_from_proto": { "total": 0.03644125299865664, "count": 30, "is_parallel": true, "self": 0.006973879003908223, "children": { "_process_rank_one_or_two_observation": { "total": 0.029467373994748414, "count": 120, "is_parallel": true, "self": 0.029467373994748414 } } } } } } } } }, "trainer_advance": { "total": 1668.8088218360379, "count": 214517, "self": 40.49114764599585, "children": { "process_trajectory": { "total": 805.2076311340425, "count": 214517, "self": 803.2075128010435, "children": { "RLTrainer._checkpoint": { "total": 2.000118332998909, "count": 6, "self": 2.000118332998909 } } }, "_update_policy": { "total": 823.1100430559994, "count": 149, "self": 477.9641945340094, "children": { "TorchPOCAOptimizer.update": { "total": 345.14584852199005, "count": 4470, "self": 345.14584852199005 } } } } } } }, "trainer_threads": { "total": 1.258999873243738e-06, "count": 1, "self": 1.258999873243738e-06 }, "TrainerController._save_models": { "total": 0.0015301299999919138, "count": 1, "self": 4.5572000090032816e-05, "children": { "RLTrainer._checkpoint": { "total": 0.001484557999901881, "count": 1, "self": 0.001484557999901881 } } } } } } }