{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7887107133865356, "min": 1.7401293516159058, "max": 3.2956771850585938, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36918.98828125, "min": 18901.3671875, "max": 116200.859375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.15, "min": 37.82170542635659, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19660.0, "min": 14620.0, "max": 25556.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1531.4205835597209, "min": 1194.702578332628, "max": 1539.0561500983504, "count": 485 }, "SoccerTwos.Self-play.ELO.sum": { "value": 306284.11671194417, "min": 2390.4195902170745, "max": 388474.362142751, "count": 485 }, "SoccerTwos.Step.mean": { "value": 4999990.0, "min": 9796.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999990.0, "min": 9796.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04663490504026413, "min": -0.08885015547275543, "max": 0.1714567095041275, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 9.280345916748047, "min": -16.17072868347168, "max": 26.98613739013672, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.044464875012636185, "min": -0.0916181281208992, "max": 0.17443154752254486, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.848509788513184, "min": -16.67449951171875, "max": 27.263031005859375, "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": 0.1385507571637331, "min": -0.45454545454545453, "max": 0.4003999959677458, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 27.571600675582886, "min": -48.49199956655502, "max": 63.40000021457672, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1385507571637331, "min": -0.45454545454545453, "max": 0.4003999959677458, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 27.571600675582886, "min": -48.49199956655502, "max": 63.40000021457672, "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": 0.01687540134492641, "min": 0.011279614374507219, "max": 0.023840051672110955, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01687540134492641, "min": 0.011279614374507219, "max": 0.023840051672110955, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11335133165121078, "min": 4.979466022329386e-06, "max": 0.13053912172714868, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11335133165121078, "min": 4.979466022329386e-06, "max": 0.13053912172714868, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.114645204693079, "min": 4.979710039757871e-06, "max": 0.1331849565108617, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.114645204693079, "min": 4.979710039757871e-06, "max": 0.1331849565108617, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704375270", "python_version": "3.8.8 (default, Apr 13 2021, 15:08:03) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\gunay\\AppData\\Roaming\\Python\\Python38\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.29.0", "mlagents_envs_version": "0.29.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1704389730" }, "total": 14460.993648500002, "count": 1, "self": 0.5239743000020098, "children": { "run_training.setup": { "total": 0.1581399000000001, "count": 1, "self": 0.1581399000000001 }, "TrainerController.start_learning": { "total": 14460.311534299999, "count": 1, "self": 8.69029659953776, "children": { "TrainerController._reset_env": { "total": 12.245709099997459, "count": 25, "self": 12.245709099997459 }, "TrainerController.advance": { "total": 14439.179738400462, "count": 342052, "self": 9.361219800872277, "children": { "env_step": { "total": 10056.881303500293, "count": 342052, "self": 5958.232203200462, "children": { "SubprocessEnvManager._take_step": { "total": 4092.7467428000336, "count": 342052, "self": 52.40351129961027, "children": { "TorchPolicy.evaluate": { "total": 4040.3432315004234, "count": 631498, "self": 839.3923616998927, "children": { "TorchPolicy.sample_actions": { "total": 3200.9508698005307, "count": 631498, "self": 3200.9508698005307 } } } } }, "workers": { "total": 5.902357499797358, "count": 342052, "self": 0.0, "children": { "worker_root": { "total": 14440.034735199612, "count": 342052, "is_parallel": true, "self": 9566.935090999767, "children": { "steps_from_proto": { "total": 0.05496520000325855, "count": 50, "is_parallel": true, "self": 0.01255280000639658, "children": { "_process_rank_one_or_two_observation": { "total": 0.04241239999686197, "count": 200, "is_parallel": true, "self": 0.04241239999686197 } } }, "UnityEnvironment.step": { "total": 4873.0446789998405, "count": 342052, "is_parallel": true, "self": 215.98587150051935, "children": { "UnityEnvironment._generate_step_input": { "total": 169.83151209952985, "count": 342052, "is_parallel": true, "self": 169.83151209952985 }, "communicator.exchange": { "total": 3764.174994200047, "count": 342052, "is_parallel": true, "self": 3764.174994200047 }, "steps_from_proto": { "total": 723.0523011997445, "count": 684104, "is_parallel": true, "self": 166.9193717983958, "children": { "_process_rank_one_or_two_observation": { "total": 556.1329294013487, "count": 2736416, "is_parallel": true, "self": 556.1329294013487 } } } } } } } } } } }, "trainer_advance": { "total": 4372.937215099297, "count": 342052, "self": 58.51805759905619, "children": { "process_trajectory": { "total": 2113.924786000248, "count": 342052, "self": 2111.3173741002483, "children": { "RLTrainer._checkpoint": { "total": 2.6074118999995335, "count": 10, "self": 2.6074118999995335 } } }, "_update_policy": { "total": 2200.494371499992, "count": 239, "self": 1164.0945175999755, "children": { "TorchPOCAOptimizer.update": { "total": 1036.3998539000168, "count": 7170, "self": 1036.3998539000168 } } } } } } }, "trainer_threads": { "total": 6.999998731771484e-07, "count": 1, "self": 6.999998731771484e-07 }, "TrainerController._save_models": { "total": 0.1957895000014105, "count": 1, "self": 0.0028696000008494593, "children": { "RLTrainer._checkpoint": { "total": 0.19291990000056103, "count": 1, "self": 0.19291990000056103 } } } } } } }