{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.858447551727295, "min": 0.8562191128730774, "max": 3.204357385635376, "count": 1426 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30686.685546875, "min": 13434.1328125, "max": 179370.796875, "count": 1426 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 276.0, "max": 999.0, "count": 1426 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 1104.0, "max": 28240.0, "count": 1426 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1192.775622451832, "min": 1186.0780097703073, "max": 1206.281809758689, "count": 80 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2385.551244903664, "min": 2372.1560195406146, "max": 14305.719416506243, "count": 80 }, "SoccerTwos.Step.mean": { "value": 21679222.0, "min": 7429794.0, "max": 21679222.0, "count": 1426 }, "SoccerTwos.Step.sum": { "value": 21679222.0, "min": 7429794.0, "max": 21679222.0, "count": 1426 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0015860110288485885, "min": -0.03300626948475838, "max": 0.002437777118757367, "count": 1426 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.01586011052131653, "min": -0.4290814995765686, "max": 0.024377770721912384, "count": 1426 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0015952929388731718, "min": -0.03303126245737076, "max": 0.0022892130073159933, "count": 1426 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.015952929854393005, "min": -0.42940640449523926, "max": 0.02289213053882122, "count": 1426 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1426 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1426 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6666666666666666, "max": 0.22958460908669692, "count": 1426 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -10.0, "max": 2.98459991812706, "count": 1426 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6666666666666666, "max": 0.22958460908669692, "count": 1426 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -10.0, "max": 2.98459991812706, "count": 1426 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1426 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1426 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01903152364733008, "min": 0.010264369505845632, "max": 0.02609913217990349, "count": 651 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01903152364733008, "min": 0.010264369505845632, "max": 0.02609913217990349, "count": 651 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.072296975500857e-08, "min": 1.4381100274749963e-11, "max": 0.004640070341217021, "count": 651 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.072296975500857e-08, "min": 1.4381100274749963e-11, "max": 0.004640070341217021, "count": 651 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.046845244407791e-08, "min": 1.869307584880427e-11, "max": 0.004646581714041531, "count": 651 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.046845244407791e-08, "min": 1.869307584880427e-11, "max": 0.004646581714041531, "count": 651 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 651 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 651 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 651 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 651 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 651 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 651 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724582597", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/poca/SoccerTwos_monti-python.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics --resume", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1724614691" }, "total": 32093.904947411982, "count": 1, "self": 4.165521894974518, "children": { "run_training.setup": { "total": 0.03884438700333703, "count": 1, "self": 0.03884438700333703 }, "TrainerController.start_learning": { "total": 32089.700581130004, "count": 1, "self": 19.33149866956228, "children": { "TrainerController._reset_env": { "total": 14.322139700889238, "count": 72, "self": 14.322139700889238 }, "TrainerController.advance": { "total": 32055.80913507055, "count": 928021, "self": 21.733378148725023, "children": { "env_step": { "total": 26282.779153292184, "count": 928021, "self": 16354.79527279995, "children": { "SubprocessEnvManager._take_step": { "total": 9914.268397079664, "count": 928021, "self": 163.38794265690376, "children": { "TorchPolicy.evaluate": { "total": 9750.88045442276, "count": 1843301, "self": 9750.88045442276 } } }, "workers": { "total": 13.715483412568574, "count": 928020, "self": 0.0, "children": { "worker_root": { "total": 32041.622939642184, "count": 928020, "is_parallel": true, "self": 17993.497503570892, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005819965997943655, "count": 2, "is_parallel": true, "self": 0.0015694559551775455, "children": { "_process_rank_one_or_two_observation": { "total": 0.004250510042766109, "count": 8, "is_parallel": true, "self": 0.004250510042766109 } } }, "UnityEnvironment.step": { "total": 0.10780634600087069, "count": 1, "is_parallel": true, "self": 0.0029583440045826137, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009076459973584861, "count": 1, "is_parallel": true, "self": 0.0009076459973584861 }, "communicator.exchange": { "total": 0.10096871899440885, "count": 1, "is_parallel": true, "self": 0.10096871899440885 }, "steps_from_proto": { "total": 0.002971637004520744, "count": 2, "is_parallel": true, "self": 0.0007164519920479506, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022551850124727935, "count": 8, "is_parallel": true, "self": 0.0022551850124727935 } } } } } } }, "steps_from_proto": { "total": 0.10211113910190761, "count": 142, "is_parallel": true, "self": 0.02299245135509409, "children": { "_process_rank_one_or_two_observation": { "total": 0.07911868774681352, "count": 568, "is_parallel": true, "self": 0.07911868774681352 } } }, "UnityEnvironment.step": { "total": 14048.02332493219, "count": 928019, "is_parallel": true, "self": 453.432637439284, "children": { "UnityEnvironment._generate_step_input": { "total": 293.7782576743921, "count": 928019, "is_parallel": true, "self": 293.7782576743921 }, "communicator.exchange": { "total": 11874.136807199946, "count": 928019, "is_parallel": true, "self": 11874.136807199946 }, "steps_from_proto": { "total": 1426.675622618568, "count": 1856038, "is_parallel": true, "self": 310.5753293937596, "children": { "_process_rank_one_or_two_observation": { "total": 1116.1002932248084, "count": 7424152, "is_parallel": true, "self": 1116.1002932248084 } } } } } } } } } } }, "trainer_advance": { "total": 5751.296603629642, "count": 928020, "self": 175.50496283953544, "children": { "process_trajectory": { "total": 2013.2323555843031, "count": 928020, "self": 2004.3198484042514, "children": { "RLTrainer._checkpoint": { "total": 8.912507180051762, "count": 29, "self": 8.912507180051762 } } }, "_update_policy": { "total": 3562.5592852058035, "count": 652, "self": 1994.2416836644697, "children": { "TorchPOCAOptimizer.update": { "total": 1568.3176015413337, "count": 19560, "self": 1568.3176015413337 } } } } } } }, "trainer_threads": { "total": 1.2509990483522415e-06, "count": 1, "self": 1.2509990483522415e-06 }, "TrainerController._save_models": { "total": 0.23780643800273538, "count": 1, "self": 0.00804893599706702, "children": { "RLTrainer._checkpoint": { "total": 0.22975750200566836, "count": 1, "self": 0.22975750200566836 } } } } } } }