{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9413414001464844, "min": 1.9219307899475098, "max": 3.2957632541656494, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36031.296875, "min": 25531.12890625, "max": 127971.15625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.82608695652173, "min": 39.1031746031746, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19548.0, "min": 16752.0, "max": 23424.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1594.395379551294, "min": 1193.9995548972622, "max": 1615.9180050412028, "count": 449 }, "SoccerTwos.Self-play.ELO.sum": { "value": 220026.56237807855, "min": 2388.0272365216433, "max": 393709.4403490699, "count": 449 }, "SoccerTwos.Step.mean": { "value": 4999972.0, "min": 9420.0, "max": 4999972.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999972.0, "min": 9420.0, "max": 4999972.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.061559468507766724, "min": -0.09887038916349411, "max": 0.2031966596841812, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.495206832885742, "min": -18.472339630126953, "max": 25.67088508605957, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06305336952209473, "min": -0.10456878691911697, "max": 0.1984257698059082, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.701364517211914, "min": -19.554363250732422, "max": 25.3031005859375, "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": -0.1422898549100627, "min": -0.7937250006943941, "max": 0.7700651163278625, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.635999977588654, "min": -44.221599817276, "max": 56.50000035762787, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1422898549100627, "min": -0.7937250006943941, "max": 0.7700651163278625, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.635999977588654, "min": -44.221599817276, "max": 56.50000035762787, "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": 0.02205762628291268, "min": 0.011046779449194825, "max": 0.02294320516521111, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02205762628291268, "min": 0.011046779449194825, "max": 0.02294320516521111, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.107183688133955, "min": 6.674084583361643e-07, "max": 0.12261001765727997, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.107183688133955, "min": 6.674084583361643e-07, "max": 0.12261001765727997, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10806383192539215, "min": 6.766215089252607e-07, "max": 0.12640023678541185, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10806383192539215, "min": 6.766215089252607e-07, "max": 0.12640023678541185, "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": "1685423701", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "D:\\Installed Programs\\anaconda3\\envs\\rl_soccertwos\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_run3 --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": "1685441418" }, "total": 17717.299978400002, "count": 1, "self": 1.4645478000020375, "children": { "run_training.setup": { "total": 0.1814509000000002, "count": 1, "self": 0.1814509000000002 }, "TrainerController.start_learning": { "total": 17715.6539797, "count": 1, "self": 9.264202500104147, "children": { "TrainerController._reset_env": { "total": 6.223417400002625, "count": 25, "self": 6.223417400002625 }, "TrainerController.advance": { "total": 17699.926608199894, "count": 338267, "self": 9.060717900087184, "children": { "env_step": { "total": 7175.445352800298, "count": 338267, "self": 5620.250890899776, "children": { "SubprocessEnvManager._take_step": { "total": 1548.9971760003177, "count": 338267, "self": 51.296062800042364, "children": { "TorchPolicy.evaluate": { "total": 1497.7011132002754, "count": 632140, "self": 1497.7011132002754 } } }, "workers": { "total": 6.197285900204077, "count": 338267, "self": 0.0, "children": { "worker_root": { "total": 17698.784214700205, "count": 338267, "is_parallel": true, "self": 13180.55582270059, "children": { "steps_from_proto": { "total": 0.050795700003899213, "count": 50, "is_parallel": true, "self": 0.010269799989711892, "children": { "_process_rank_one_or_two_observation": { "total": 0.04052590001418732, "count": 200, "is_parallel": true, "self": 0.04052590001418732 } } }, "UnityEnvironment.step": { "total": 4518.177596299611, "count": 338267, "is_parallel": true, "self": 208.22896529913942, "children": { "UnityEnvironment._generate_step_input": { "total": 169.85250920052027, "count": 338267, "is_parallel": true, "self": 169.85250920052027 }, "communicator.exchange": { "total": 3461.3960718001867, "count": 338267, "is_parallel": true, "self": 3461.3960718001867 }, "steps_from_proto": { "total": 678.7000499997645, "count": 676534, "is_parallel": true, "self": 137.4947882996629, "children": { "_process_rank_one_or_two_observation": { "total": 541.2052617001016, "count": 2706136, "is_parallel": true, "self": 541.2052617001016 } } } } } } } } } } }, "trainer_advance": { "total": 10515.42053749951, "count": 338267, "self": 61.660088999846266, "children": { "process_trajectory": { "total": 1482.960089999666, "count": 338267, "self": 1480.6348724996637, "children": { "RLTrainer._checkpoint": { "total": 2.3252175000022817, "count": 10, "self": 2.3252175000022817 } } }, "_update_policy": { "total": 8970.800358499999, "count": 239, "self": 852.3167408000272, "children": { "TorchPOCAOptimizer.update": { "total": 8118.483617699972, "count": 7170, "self": 8118.483617699972 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.23975069999869447, "count": 1, "self": 0.009434100000362378, "children": { "RLTrainer._checkpoint": { "total": 0.2303165999983321, "count": 1, "self": 0.2303165999983321 } } } } } } }