{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8810371160507202, "min": 1.8810371160507202, "max": 3.2957165241241455, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37861.515625, "min": 21933.12890625, "max": 119398.3125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.43333333333333, "min": 40.975, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19596.0, "min": 16432.0, "max": 24828.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1569.255753048845, "min": 1198.9219741832458, "max": 1579.3357281804326, "count": 497 }, "SoccerTwos.Self-play.ELO.sum": { "value": 282466.0355487921, "min": 2403.5350145701996, "max": 361941.7647455753, "count": 497 }, "SoccerTwos.Step.mean": { "value": 4999995.0, "min": 9432.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999995.0, "min": 9432.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05710319057106972, "min": -0.091892771422863, "max": 0.27343571186065674, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.278573989868164, "min": -18.010982513427734, "max": 33.758819580078125, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.060045454651117325, "min": -0.09204566478729248, "max": 0.27183154225349426, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.808181762695312, "min": -18.040950775146484, "max": 32.77088165283203, "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": -0.20300222304132248, "min": -0.6648521734320599, "max": 0.5065971831200828, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -36.54040014743805, "min": -45.763999700546265, "max": 65.63139963150024, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.20300222304132248, "min": -0.6648521734320599, "max": 0.5065971831200828, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -36.54040014743805, "min": -45.763999700546265, "max": 65.63139963150024, "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": 0.016971885614718, "min": 0.010800089661885674, "max": 0.023821953497827054, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016971885614718, "min": 0.010800089661885674, "max": 0.023821953497827054, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10521893799304963, "min": 0.00178584005140389, "max": 0.11642369578282039, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10521893799304963, "min": 0.00178584005140389, "max": 0.11642369578282039, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10675618723034859, "min": 0.0017965215258300305, "max": 0.1185242474079132, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10675618723034859, "min": 0.0017965215258300305, "max": 0.1185242474079132, "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": "1728360053", "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:\\ProgramData\\anaconda3\\envs\\hf_rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos0 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1728375798" }, "total": 15745.179080599999, "count": 1, "self": 0.3061478000090574, "children": { "run_training.setup": { "total": 0.17916519999562297, "count": 1, "self": 0.17916519999562297 }, "TrainerController.start_learning": { "total": 15744.693767599994, "count": 1, "self": 8.793921397103986, "children": { "TrainerController._reset_env": { "total": 7.95673589999933, "count": 25, "self": 7.95673589999933 }, "TrainerController.advance": { "total": 15727.745772702881, "count": 344560, "self": 8.997947603376815, "children": { "env_step": { "total": 10219.313987399466, "count": 344560, "self": 5132.117217297273, "children": { "SubprocessEnvManager._take_step": { "total": 5081.874307201215, "count": 344560, "self": 57.17382360048214, "children": { "TorchPolicy.evaluate": { "total": 5024.700483600733, "count": 628624, "self": 5024.700483600733 } } }, "workers": { "total": 5.32246290097828, "count": 344560, "self": 0.0, "children": { "worker_root": { "total": 15726.28423610131, "count": 344560, "is_parallel": true, "self": 11629.854785000818, "children": { "steps_from_proto": { "total": 0.052442700012761634, "count": 50, "is_parallel": true, "self": 0.010369500043452717, "children": { "_process_rank_one_or_two_observation": { "total": 0.042073199969308916, "count": 200, "is_parallel": true, "self": 0.042073199969308916 } } }, "UnityEnvironment.step": { "total": 4096.377008400479, "count": 344560, "is_parallel": true, "self": 208.92783670135395, "children": { "UnityEnvironment._generate_step_input": { "total": 154.53004000180226, "count": 344560, "is_parallel": true, "self": 154.53004000180226 }, "communicator.exchange": { "total": 3063.5470115963253, "count": 344560, "is_parallel": true, "self": 3063.5470115963253 }, "steps_from_proto": { "total": 669.3721201009976, "count": 689120, "is_parallel": true, "self": 135.8808712961254, "children": { "_process_rank_one_or_two_observation": { "total": 533.4912488048722, "count": 2756480, "is_parallel": true, "self": 533.4912488048722 } } } } } } } } } } }, "trainer_advance": { "total": 5499.433837700039, "count": 344560, "self": 58.7371944018887, "children": { "process_trajectory": { "total": 2142.6032162981646, "count": 344560, "self": 2140.3276326981722, "children": { "RLTrainer._checkpoint": { "total": 2.2755835999923875, "count": 10, "self": 2.2755835999923875 } } }, "_update_policy": { "total": 3298.0934269999852, "count": 241, "self": 839.62336110037, "children": { "TorchPOCAOptimizer.update": { "total": 2458.4700658996153, "count": 7230, "self": 2458.4700658996153 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.19733670000277925, "count": 1, "self": 0.002516300002753269, "children": { "RLTrainer._checkpoint": { "total": 0.19482040000002598, "count": 1, "self": 0.19482040000002598 } } } } } } }