{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9306962490081787, "min": 1.8911863565444946, "max": 3.2957510948181152, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38490.359375, "min": 16988.080078125, "max": 154150.9375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.0, "min": 43.73873873873874, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19588.0, "min": 16000.0, "max": 23596.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1504.6975457660337, "min": 1196.9601544507059, "max": 1568.8141767438449, "count": 486 }, "SoccerTwos.Self-play.ELO.sum": { "value": 249779.7925971616, "min": 2393.9203089014118, "max": 341822.3946120857, "count": 486 }, "SoccerTwos.Step.mean": { "value": 4999868.0, "min": 9248.0, "max": 4999868.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999868.0, "min": 9248.0, "max": 4999868.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09636995941400528, "min": -0.09636995941400528, "max": 0.22153037786483765, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -15.997413635253906, "min": -17.75470542907715, "max": 35.001800537109375, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10343483835458755, "min": -0.10343483835458755, "max": 0.2321692407131195, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -17.170183181762695, "min": -19.177967071533203, "max": 36.6827392578125, "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": -0.22937831390334898, "min": -0.7277125008404255, "max": 0.4492222269376119, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -38.07680010795593, "min": -65.17960000038147, "max": 52.24399995803833, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.22937831390334898, "min": -0.7277125008404255, "max": 0.4492222269376119, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -38.07680010795593, "min": -65.17960000038147, "max": 52.24399995803833, "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": 0.018552274740553307, "min": 0.010510871760197915, "max": 0.022960713635742043, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018552274740553307, "min": 0.010510871760197915, "max": 0.022960713635742043, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09403324102361997, "min": 5.234845824209818e-05, "max": 0.1141713410615921, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09403324102361997, "min": 5.234845824209818e-05, "max": 0.1141713410615921, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09515002643068632, "min": 5.1456666430264404e-05, "max": 0.11636882200837136, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09515002643068632, "min": 5.1456666430264404e-05, "max": 0.11636882200837136, "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": "1731436326", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env /content/training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id SoccerTwos-run-1 --torch-device cuda:0 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731456427" }, "total": 20102.200962941017, "count": 1, "self": 0.8466040030180011, "children": { "run_training.setup": { "total": 0.0457150120055303, "count": 1, "self": 0.0457150120055303 }, "TrainerController.start_learning": { "total": 20101.308643925993, "count": 1, "self": 13.615007028391119, "children": { "TrainerController._reset_env": { "total": 10.937195231206715, "count": 25, "self": 10.937195231206715 }, "TrainerController.advance": { "total": 20076.384856074408, "count": 338345, "self": 14.545604879851453, "children": { "env_step": { "total": 16323.718732788751, "count": 338345, "self": 10768.747881692165, "children": { "SubprocessEnvManager._take_step": { "total": 5546.310173749778, "count": 338345, "self": 89.78759291832102, "children": { "TorchPolicy.evaluate": { "total": 5456.522580831457, "count": 633200, "self": 5456.522580831457 } } }, "workers": { "total": 8.66067734680837, "count": 338345, "self": 0.0, "children": { "worker_root": { "total": 20074.35006287234, "count": 338345, "is_parallel": true, "self": 10809.206183887902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00293175398837775, "count": 2, "is_parallel": true, "self": 0.0008348850242327899, "children": { "_process_rank_one_or_two_observation": { "total": 0.00209686896414496, "count": 8, "is_parallel": true, "self": 0.00209686896414496 } } }, "UnityEnvironment.step": { "total": 0.0517104429891333, "count": 1, "is_parallel": true, "self": 0.0007486299728043377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005300490010995418, "count": 1, "is_parallel": true, "self": 0.0005300490010995418 }, "communicator.exchange": { "total": 0.04757096301182173, "count": 1, "is_parallel": true, "self": 0.04757096301182173 }, "steps_from_proto": { "total": 0.002860801003407687, "count": 2, "is_parallel": true, "self": 0.0007514899771194905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021093110262881964, "count": 8, "is_parallel": true, "self": 0.0021093110262881964 } } } } } } }, "UnityEnvironment.step": { "total": 9265.070866913447, "count": 338344, "is_parallel": true, "self": 290.4113600043929, "children": { "UnityEnvironment._generate_step_input": { "total": 179.64585285322391, "count": 338344, "is_parallel": true, "self": 179.64585285322391 }, "communicator.exchange": { "total": 7943.700120455032, "count": 338344, "is_parallel": true, "self": 7943.700120455032 }, "steps_from_proto": { "total": 851.3135336007981, "count": 676688, "is_parallel": true, "self": 191.40494748813217, "children": { "_process_rank_one_or_two_observation": { "total": 659.908586112666, "count": 2706752, "is_parallel": true, "self": 659.908586112666 } } } } }, "steps_from_proto": { "total": 0.07301207099226303, "count": 48, "is_parallel": true, "self": 0.016617817018413916, "children": { "_process_rank_one_or_two_observation": { "total": 0.05639425397384912, "count": 192, "is_parallel": true, "self": 0.05639425397384912 } } } } } } } } }, "trainer_advance": { "total": 3738.1205184058053, "count": 338345, "self": 92.06295491752098, "children": { "process_trajectory": { "total": 1960.9711744232627, "count": 338345, "self": 1956.9563712152885, "children": { "RLTrainer._checkpoint": { "total": 4.014803207974182, "count": 10, "self": 4.014803207974182 } } }, "_update_policy": { "total": 1685.0863890650216, "count": 239, "self": 906.7725982324628, "children": { "TorchPOCAOptimizer.update": { "total": 778.3137908325589, "count": 7170, "self": 778.3137908325589 } } } } } } }, "trainer_threads": { "total": 1.8299906514585018e-06, "count": 1, "self": 1.8299906514585018e-06 }, "TrainerController._save_models": { "total": 0.3715837619965896, "count": 1, "self": 0.003272816975368187, "children": { "RLTrainer._checkpoint": { "total": 0.3683109450212214, "count": 1, "self": 0.3683109450212214 } } } } } } }