{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9141000509262085, "min": 1.8692859411239624, "max": 3.2956552505493164, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37179.48046875, "min": 22639.98828125, "max": 109496.34375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.17307692307692, "min": 38.60629921259842, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19624.0, "min": 16372.0, "max": 23296.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1547.0950910470588, "min": 1202.0289780677504, "max": 1547.0950910470588, "count": 497 }, "SoccerTwos.Self-play.ELO.sum": { "value": 321795.7789377882, "min": 2407.4163685120193, "max": 379049.1712501124, "count": 497 }, "SoccerTwos.Step.mean": { "value": 4999974.0, "min": 9572.0, "max": 4999974.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999974.0, "min": 9572.0, "max": 4999974.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.10104518383741379, "min": -0.12364988774061203, "max": 0.1894615739583969, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 20.916353225708008, "min": -25.243967056274414, "max": 30.43375015258789, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09892608225345612, "min": -0.12764589488506317, "max": 0.18884459137916565, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 20.477699279785156, "min": -25.5703067779541, "max": 30.573925018310547, "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": 0.24378164263739102, "min": -0.5087764701422524, "max": 0.5708425501559643, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 50.46280002593994, "min": -64.43239986896515, "max": 63.92079997062683, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.24378164263739102, "min": -0.5087764701422524, "max": 0.5708425501559643, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 50.46280002593994, "min": -64.43239986896515, "max": 63.92079997062683, "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": 0.018066664575599134, "min": 0.011809572900043955, "max": 0.023689606642195334, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018066664575599134, "min": 0.011809572900043955, "max": 0.023689606642195334, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10926515559355418, "min": 0.00016289373258283982, "max": 0.12037126595775287, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10926515559355418, "min": 0.00016289373258283982, "max": 0.12037126595775287, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11118501350283623, "min": 0.00016918394758249632, "max": 0.1226127304136753, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11118501350283623, "min": 0.00016918394758249632, "max": 0.1226127304136753, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739367797", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\dmgp1\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force --debug", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1739383205" }, "total": 15408.2365671, "count": 1, "self": 2.0305599000021175, "children": { "run_training.setup": { "total": 0.14632140000003346, "count": 1, "self": 0.14632140000003346 }, "TrainerController.start_learning": { "total": 15406.059685799999, "count": 1, "self": 9.114420799607615, "children": { "TrainerController._reset_env": { "total": 8.760013299995535, "count": 25, "self": 8.760013299995535 }, "TrainerController.advance": { "total": 15387.999393500395, "count": 345361, "self": 9.994789901229524, "children": { "env_step": { "total": 6294.26011079961, "count": 345361, "self": 4689.526664699824, "children": { "SubprocessEnvManager._take_step": { "total": 1599.3557099994187, "count": 345361, "self": 59.62347309861616, "children": { "TorchPolicy.evaluate": { "total": 1539.7322369008025, "count": 630150, "self": 1539.7322369008025 } } }, "workers": { "total": 5.3777361003667465, "count": 345361, "self": 0.0, "children": { "worker_root": { "total": 15386.499856799719, "count": 345361, "is_parallel": true, "self": 11665.387229599466, "children": { "steps_from_proto": { "total": 0.05022050000229683, "count": 50, "is_parallel": true, "self": 0.011503100004460975, "children": { "_process_rank_one_or_two_observation": { "total": 0.038717399997835855, "count": 200, "is_parallel": true, "self": 0.038717399997835855 } } }, "UnityEnvironment.step": { "total": 3721.062406700251, "count": 345361, "is_parallel": true, "self": 180.43447409972714, "children": { "UnityEnvironment._generate_step_input": { "total": 146.6035122002778, "count": 345361, "is_parallel": true, "self": 146.6035122002778 }, "communicator.exchange": { "total": 2835.016612500043, "count": 345361, "is_parallel": true, "self": 2835.016612500043 }, "steps_from_proto": { "total": 559.0078079002031, "count": 690722, "is_parallel": true, "self": 118.82060430197475, "children": { "_process_rank_one_or_two_observation": { "total": 440.1872035982284, "count": 2762888, "is_parallel": true, "self": 440.1872035982284 } } } } } } } } } } }, "trainer_advance": { "total": 9083.744492799557, "count": 345361, "self": 61.90763759969559, "children": { "process_trajectory": { "total": 1682.4986517998532, "count": 345361, "self": 1680.3046260998544, "children": { "RLTrainer._checkpoint": { "total": 2.194025699998747, "count": 10, "self": 2.194025699998747 } } }, "_update_policy": { "total": 7339.338203400009, "count": 241, "self": 774.0372126999291, "children": { "TorchPOCAOptimizer.update": { "total": 6565.30099070008, "count": 7230, "self": 6565.30099070008 } } } } } } }, "trainer_threads": { "total": 4.200001058052294e-06, "count": 1, "self": 4.200001058052294e-06 }, "TrainerController._save_models": { "total": 0.1858539999993809, "count": 1, "self": 0.03140789999997651, "children": { "RLTrainer._checkpoint": { "total": 0.1544460999994044, "count": 1, "self": 0.1544460999994044 } } } } } } }