{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.206007957458496, "min": 2.1812851428985596, "max": 3.2957143783569336, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41508.24609375, "min": 18881.65625, "max": 140861.15625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 78.68852459016394, "min": 51.864583333333336, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19200.0, "min": 16860.0, "max": 24400.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1950.644171854746, "min": 1593.3983795883569, "max": 2115.5389198119915, "count": 4980 }, "SoccerTwos.Self-play.ELO.sum": { "value": 237978.588966279, "min": 3186.7967591767137, "max": 385631.0232119799, "count": 4980 }, "SoccerTwos.Step.mean": { "value": 49999940.0, "min": 9218.0, "max": 49999940.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999940.0, "min": 9218.0, "max": 49999940.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.060406338423490524, "min": -0.14533524215221405, "max": 0.2691265046596527, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.4299798011779785, "min": -21.218944549560547, "max": 37.40858459472656, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05984955653548241, "min": -0.1457369178533554, "max": 0.27340540289878845, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.361495494842529, "min": -21.277589797973633, "max": 38.00334930419922, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.09341788485767395, "min": -0.5714285714285714, "max": 0.5925294962718333, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.490399837493896, "min": -73.0508001446724, "max": 82.36159998178482, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.09341788485767395, "min": -0.5714285714285714, "max": 0.5925294962718333, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.490399837493896, "min": -73.0508001446724, "max": 82.36159998178482, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020830254150011267, "min": 0.011360593161468084, "max": 0.028308066849907238, "count": 2421 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020830254150011267, "min": 0.011360593161468084, "max": 0.028308066849907238, "count": 2421 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07555229018131891, "min": 3.990373528116227e-05, "max": 0.10487701868017514, "count": 2421 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07555229018131891, "min": 3.990373528116227e-05, "max": 0.10487701868017514, "count": 2421 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0765951876839002, "min": 3.904025124938926e-05, "max": 0.1067599505186081, "count": 2421 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0765951876839002, "min": 3.904025124938926e-05, "max": 0.1067599505186081, "count": 2421 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00019999999999999996, "count": 2421 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00019999999999999996, "count": 2421 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2421 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2421 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 2421 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 2421 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1730892682", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/inzaghi/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1730979300" }, "total": 86617.49148547799, "count": 1, "self": 10.00375251499645, "children": { "run_training.setup": { "total": 0.012135985001805238, "count": 1, "self": 0.012135985001805238 }, "TrainerController.start_learning": { "total": 86607.475596978, "count": 1, "self": 37.951250426413026, "children": { "TrainerController._reset_env": { "total": 5.305693432863336, "count": 250, "self": 5.305693432863336 }, "TrainerController.advance": { "total": 86564.04181900971, "count": 3395027, "self": 37.610430772663676, "children": { "env_step": { "total": 69123.40285133061, "count": 3395027, "self": 47247.077142872164, "children": { "SubprocessEnvManager._take_step": { "total": 21852.30030985897, "count": 3395027, "self": 258.01309438821045, "children": { "TorchPolicy.evaluate": { "total": 21594.28721547076, "count": 6284946, "self": 21594.28721547076 } } }, "workers": { "total": 24.02539859947865, "count": 3395027, "self": 0.0, "children": { "worker_root": { "total": 86497.62175945281, "count": 3395027, "is_parallel": true, "self": 43967.18401695874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016843830089783296, "count": 2, "is_parallel": true, "self": 0.00047450902638956904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012098739825887606, "count": 8, "is_parallel": true, "self": 0.0012098739825887606 } } }, "UnityEnvironment.step": { "total": 0.022768869006540626, "count": 1, "is_parallel": true, "self": 0.0003269459994044155, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002817630011122674, "count": 1, "is_parallel": true, "self": 0.0002817630011122674 }, "communicator.exchange": { "total": 0.02111480399616994, "count": 1, "is_parallel": true, "self": 0.02111480399616994 }, "steps_from_proto": { "total": 0.0010453560098540038, "count": 2, "is_parallel": true, "self": 0.00021642801584675908, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008289279940072447, "count": 8, "is_parallel": true, "self": 0.0008289279940072447 } } } } } } }, "UnityEnvironment.step": { "total": 42530.18156607491, "count": 3395026, "is_parallel": true, "self": 989.472904168957, "children": { "UnityEnvironment._generate_step_input": { "total": 689.5561021149333, "count": 3395026, "is_parallel": true, "self": 689.5561021149333 }, "communicator.exchange": { "total": 37894.11983573294, "count": 3395026, "is_parallel": true, "self": 37894.11983573294 }, "steps_from_proto": { "total": 2957.032724058081, "count": 6790052, "is_parallel": true, "self": 567.7807999830984, "children": { "_process_rank_one_or_two_observation": { "total": 2389.2519240749825, "count": 27160208, "is_parallel": true, "self": 2389.2519240749825 } } } } }, "steps_from_proto": { "total": 0.2561764191632392, "count": 498, "is_parallel": true, "self": 0.05038388010871131, "children": { "_process_rank_one_or_two_observation": { "total": 0.20579253905452788, "count": 1992, "is_parallel": true, "self": 0.20579253905452788 } } } } } } } } }, "trainer_advance": { "total": 17403.028536906437, "count": 3395027, "self": 354.7357740368752, "children": { "process_trajectory": { "total": 10132.702762205183, "count": 3395027, "self": 10115.555769428305, "children": { "RLTrainer._checkpoint": { "total": 17.146992776877596, "count": 100, "self": 17.146992776877596 } } }, "_update_policy": { "total": 6915.590000664379, "count": 2421, "self": 3613.9675610413833, "children": { "TorchPOCAOptimizer.update": { "total": 3301.6224396229954, "count": 72630, "self": 3301.6224396229954 } } } } } } }, "trainer_threads": { "total": 5.370238795876503e-07, "count": 1, "self": 5.370238795876503e-07 }, "TrainerController._save_models": { "total": 0.17683357198257, "count": 1, "self": 0.002149088977603242, "children": { "RLTrainer._checkpoint": { "total": 0.17468448300496675, "count": 1, "self": 0.17468448300496675 } } } } } } }