{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.888034462928772, "min": 1.8839737176895142, "max": 3.295701026916504, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36189.84375, "min": 22383.443359375, "max": 129587.9453125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 66.2, "min": 42.495652173913044, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19860.0, "min": 16288.0, "max": 24204.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1572.1872102981022, "min": 1184.478052901344, "max": 1592.9626647400569, "count": 492 }, "SoccerTwos.Self-play.ELO.sum": { "value": 235828.08154471533, "min": 2370.8995509098922, "max": 361711.2594856975, "count": 492 }, "SoccerTwos.Step.mean": { "value": 4999938.0, "min": 9118.0, "max": 4999938.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999938.0, "min": 9118.0, "max": 4999938.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.038897983729839325, "min": -0.09137722104787827, "max": 0.16010504961013794, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.795799732208252, "min": -19.467674255371094, "max": 25.771255493164062, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04155198484659195, "min": -0.09302152693271637, "max": 0.15395911037921906, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.1912455558776855, "min": -18.92449951171875, "max": 26.997636795043945, "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": -0.12965503355000643, "min": -0.6875, "max": 0.4564571423189981, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.31859999895096, "min": -48.292799949645996, "max": 66.34960043430328, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12965503355000643, "min": -0.6875, "max": 0.4564571423189981, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.31859999895096, "min": -48.292799949645996, "max": 66.34960043430328, "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": 0.013212521648771751, "min": 0.011471809999117491, "max": 0.02311958824284375, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013212521648771751, "min": 0.011471809999117491, "max": 0.02311958824284375, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1133302482465903, "min": 0.0002963844633389575, "max": 0.11887743721405665, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1133302482465903, "min": 0.0002963844633389575, "max": 0.11887743721405665, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11473574340343476, "min": 0.0002984581199901489, "max": 0.1206396073102951, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11473574340343476, "min": 0.0002984581199901489, "max": 0.1206396073102951, "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": 0.20000000000000004, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "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": "1741529132", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/tmoroder/miniconda3/envs/soccer2/bin/mlagents-learn ./SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741536540" }, "total": 7681.631621897999, "count": 1, "self": 0.16835441299826925, "children": { "run_training.setup": { "total": 0.010236830999929225, "count": 1, "self": 0.010236830999929225 }, "TrainerController.start_learning": { "total": 7681.453030654001, "count": 1, "self": 3.9973651684458673, "children": { "TrainerController._reset_env": { "total": 1.6367854609979986, "count": 25, "self": 1.6367854609979986 }, "TrainerController.advance": { "total": 7675.685232209558, "count": 338193, "self": 3.4089553699359385, "children": { "env_step": { "total": 6307.022652871789, "count": 338193, "self": 4065.376180029698, "children": { "SubprocessEnvManager._take_step": { "total": 2238.8586767692386, "count": 338193, "self": 24.097139889209757, "children": { "TorchPolicy.evaluate": { "total": 2214.761536880029, "count": 632126, "self": 2214.761536880029 } } }, "workers": { "total": 2.7877960728528706, "count": 338193, "self": 0.0, "children": { "worker_root": { "total": 7671.364744498982, "count": 338193, "is_parallel": true, "self": 4047.0129173419655, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015126469997994718, "count": 2, "is_parallel": true, "self": 0.00036720199841511203, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011454450013843598, "count": 8, "is_parallel": true, "self": 0.0011454450013843598 } } }, "UnityEnvironment.step": { "total": 0.01832624000053329, "count": 1, "is_parallel": true, "self": 0.00026339000032749027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022268100019573467, "count": 1, "is_parallel": true, "self": 0.00022268100019573467 }, "communicator.exchange": { "total": 0.01695224800005235, "count": 1, "is_parallel": true, "self": 0.01695224800005235 }, "steps_from_proto": { "total": 0.0008879209999577142, "count": 2, "is_parallel": true, "self": 0.00021439200008899206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006735289998687222, "count": 8, "is_parallel": true, "self": 0.0006735289998687222 } } } } } } }, "UnityEnvironment.step": { "total": 3624.3308839780184, "count": 338192, "is_parallel": true, "self": 82.35042984910888, "children": { "UnityEnvironment._generate_step_input": { "total": 51.97169326825133, "count": 338192, "is_parallel": true, "self": 51.97169326825133 }, "communicator.exchange": { "total": 3234.4415439956065, "count": 338192, "is_parallel": true, "self": 3234.4415439956065 }, "steps_from_proto": { "total": 255.5672168650517, "count": 676384, "is_parallel": true, "self": 53.84672836861955, "children": { "_process_rank_one_or_two_observation": { "total": 201.72048849643215, "count": 2705536, "is_parallel": true, "self": 201.72048849643215 } } } } }, "steps_from_proto": { "total": 0.02094317899809539, "count": 48, "is_parallel": true, "self": 0.004477624999708496, "children": { "_process_rank_one_or_two_observation": { "total": 0.016465553998386895, "count": 192, "is_parallel": true, "self": 0.016465553998386895 } } } } } } } } }, "trainer_advance": { "total": 1365.253623967833, "count": 338193, "self": 35.61094824255906, "children": { "process_trajectory": { "total": 742.399001000269, "count": 338193, "self": 741.1648644102706, "children": { "RLTrainer._checkpoint": { "total": 1.234136589998343, "count": 10, "self": 1.234136589998343 } } }, "_update_policy": { "total": 587.2436747250049, "count": 239, "self": 291.6783001959975, "children": { "TorchPOCAOptimizer.update": { "total": 295.5653745290074, "count": 7179, "self": 295.5653745290074 } } } } } } }, "trainer_threads": { "total": 4.689991328632459e-07, "count": 1, "self": 4.689991328632459e-07 }, "TrainerController._save_models": { "total": 0.13364734599963413, "count": 1, "self": 0.001086107999071828, "children": { "RLTrainer._checkpoint": { "total": 0.1325612380005623, "count": 1, "self": 0.1325612380005623 } } } } } } }