{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2623162269592285, "min": 3.2615444660186768, "max": 3.2957561016082764, "count": 16 }, "SoccerTwos.Policy.Entropy.sum": { "value": 68691.328125, "min": 40394.92578125, "max": 105464.1875, "count": 16 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 601.7777777777778, "min": 574.4, "max": 999.0, "count": 16 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21664.0, "min": 11488.0, "max": 28988.0, "count": 16 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.3408982701842, "min": 1197.3408982701842, "max": 1203.8175274476016, "count": 15 }, "SoccerTwos.Self-play.ELO.sum": { "value": 14368.090779242211, "min": 2396.1535795422496, "max": 14368.090779242211, "count": 15 }, "SoccerTwos.Step.mean": { "value": 159824.0, "min": 9512.0, "max": 159824.0, "count": 16 }, "SoccerTwos.Step.sum": { "value": 159824.0, "min": 9512.0, "max": 159824.0, "count": 16 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.026351574808359146, "min": -0.05036341771483421, "max": -0.026351574808359146, "count": 16 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.4479767680168152, "min": -0.7428839206695557, "max": -0.3202369809150696, "count": 16 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.025530071929097176, "min": -0.050388529896736145, "max": -0.025530071929097176, "count": 16 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.43401122093200684, "min": -0.7053990960121155, "max": -0.34283724427223206, "count": 16 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 16 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 16 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05778823179357192, "min": -0.3965142858879907, "max": 0.2683384601886456, "count": 16 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.9823999404907227, "min": -5.5512000024318695, "max": 3.4883999824523926, "count": 16 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05778823179357192, "min": -0.3965142858879907, "max": 0.2683384601886456, "count": 16 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.9823999404907227, "min": -5.5512000024318695, "max": 3.4883999824523926, "count": 16 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016798803419806062, "min": 0.013983288051288885, "max": 0.019427612053308015, "count": 7 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016798803419806062, "min": 0.013983288051288885, "max": 0.019427612053308015, "count": 7 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003357618247779707, "min": 0.0016571837554996212, "max": 0.0046502520640691125, "count": 7 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003357618247779707, "min": 0.0016571837554996212, "max": 0.0046502520640691125, "count": 7 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0033834061313730976, "min": 0.0017213587920802335, "max": 0.004764475013750295, "count": 7 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0033834061313730976, "min": 0.0017213587920802335, "max": 0.004764475013750295, "count": 7 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 7 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 7 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 7 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 7 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 7 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685065634", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\PC-Admin\\Anaconda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1685073174" }, "total": 7540.803681587, "count": 1, "self": 0.11845842399907269, "children": { "run_training.setup": { "total": 3.098007620000004, "count": 1, "self": 3.098007620000004 }, "TrainerController.start_learning": { "total": 7537.587215543001, "count": 1, "self": 0.819069577953087, "children": { "TrainerController._reset_env": { "total": 92.219704239, "count": 1, "self": 92.219704239 }, "TrainerController.advance": { "total": 7433.0073113540475, "count": 10834, "self": 0.8331230440899162, "children": { "env_step": { "total": 6008.036598750998, "count": 10834, "self": 5817.722961007964, "children": { "SubprocessEnvManager._take_step": { "total": 189.78471672804437, "count": 10834, "self": 6.030594909089899, "children": { "TorchPolicy.evaluate": { "total": 183.75412181895447, "count": 21504, "self": 183.75412181895447 } } }, "workers": { "total": 0.5289210149895496, "count": 10833, "self": 0.0, "children": { "worker_root": { "total": 7434.3655564799865, "count": 10833, "is_parallel": true, "self": 1727.325292816975, "children": { "steps_from_proto": { "total": 0.02151822899999445, "count": 2, "is_parallel": true, "self": 0.002809094999975059, "children": { "_process_rank_one_or_two_observation": { "total": 0.01870913400001939, "count": 8, "is_parallel": true, "self": 0.01870913400001939 } } }, "UnityEnvironment.step": { "total": 5707.018745434011, "count": 10833, "is_parallel": true, "self": 10.761603176963035, "children": { "UnityEnvironment._generate_step_input": { "total": 122.15321961302764, "count": 10833, "is_parallel": true, "self": 122.15321961302764 }, "communicator.exchange": { "total": 5369.75882440797, "count": 10833, "is_parallel": true, "self": 5369.75882440797 }, "steps_from_proto": { "total": 204.34509823605106, "count": 21666, "is_parallel": true, "self": 23.157507915941096, "children": { "_process_rank_one_or_two_observation": { "total": 181.18759032010996, "count": 86664, "is_parallel": true, "self": 181.18759032010996 } } } } } } } } } } }, "trainer_advance": { "total": 1424.1375895589601, "count": 10833, "self": 4.837865171013618, "children": { "process_trajectory": { "total": 196.17368740894636, "count": 10833, "self": 196.17368740894636 }, "_update_policy": { "total": 1223.1260369790002, "count": 7, "self": 103.8595243900022, "children": { "TorchPOCAOptimizer.update": { "total": 1119.266512588998, "count": 210, "self": 1119.266512588998 } } } } } } }, "trainer_threads": { "total": 1.9740000425372273e-06, "count": 1, "self": 1.9740000425372273e-06 }, "TrainerController._save_models": { "total": 11.541128398000183, "count": 1, "self": 6.315999962680507e-05, "children": { "RLTrainer._checkpoint": { "total": 11.541065238000556, "count": 1, "self": 11.541065238000556 } } } } } } }