{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.1379538774490356, "min": 0.9347377419471741, "max": 1.2154386043548584, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 22759.078125, "min": 16144.0087890625, "max": 28788.599609375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 77.0, "min": 47.0, "max": 109.45652173913044, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20328.0, "min": 17524.0, "max": 22004.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1796.1838299057483, "min": 1766.9128790251336, "max": 2009.782144467024, "count": 5000 }, "SoccerTwos.Self-play.ELO.sum": { "value": 237096.26554755878, "min": 162464.24892216737, "max": 408058.2623436854, "count": 5000 }, "SoccerTwos.Step.mean": { "value": 199999836.0, "min": 150009962.0, "max": 199999836.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 199999836.0, "min": 150009962.0, "max": 199999836.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006698582321405411, "min": -0.13151130080223083, "max": 0.11459764093160629, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.884212851524353, "min": -20.03160285949707, "max": 15.929072380065918, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.008320164866745472, "min": -0.13271933794021606, "max": 0.1126069650053978, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.0982617139816284, "min": -19.85004234313965, "max": 15.652368545532227, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09068181839856235, "min": -0.4092910343203051, "max": 0.3747726631679123, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.97000002861023, "min": -65.99200028181076, "max": 55.140800297260284, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09068181839856235, "min": -0.4092910343203051, "max": 0.3747726631679123, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.97000002861023, "min": -65.99200028181076, "max": 55.140800297260284, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01593884900600339, "min": 0.01253225206813416, "max": 0.026699458491930273, "count": 2426 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01593884900600339, "min": 0.01253225206813416, "max": 0.026699458491930273, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0718688689172268, "min": 0.05997977815568447, "max": 0.11612731764713922, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0718688689172268, "min": 0.05997977815568447, "max": 0.11612731764713922, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07221189687649408, "min": 0.06059066231052081, "max": 0.11714418778816858, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07221189687649408, "min": 0.06059066231052081, "max": 0.11714418778816858, "count": 2426 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688012068", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/home/yoav/anaconda3/envs/2vs2_soccer/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688083976" }, "total": 71907.872196146, "count": 1, "self": 0.21947479801019654, "children": { "run_training.setup": { "total": 0.008186355989892036, "count": 1, "self": 0.008186355989892036 }, "TrainerController.start_learning": { "total": 71907.644534992, "count": 1, "self": 71.42090288587497, "children": { "TrainerController._reset_env": { "total": 7.242712540260982, "count": 251, "self": 7.242712540260982 }, "TrainerController.advance": { "total": 71828.76494877986, "count": 3422862, "self": 66.44977636545082, "children": { "env_step": { "total": 51541.429678388406, "count": 3422862, "self": 37821.549245519214, "children": { "SubprocessEnvManager._take_step": { "total": 13680.694317420828, "count": 3422862, "self": 372.45103261907934, "children": { "TorchPolicy.evaluate": { "total": 13308.243284801749, "count": 6278128, "self": 13308.243284801749 } } }, "workers": { "total": 39.186115448363125, "count": 3422862, "self": 0.0, "children": { "worker_root": { "total": 71820.2092914654, "count": 3422862, "is_parallel": true, "self": 41044.5662780235, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017572160286363214, "count": 2, "is_parallel": true, "self": 0.00041944000986404717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013377760187722743, "count": 8, "is_parallel": true, "self": 0.0013377760187722743 } } }, "UnityEnvironment.step": { "total": 0.024257199984276667, "count": 1, "is_parallel": true, "self": 0.0006558480090461671, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032233400270342827, "count": 1, "is_parallel": true, "self": 0.00032233400270342827 }, "communicator.exchange": { "total": 0.02124975499464199, "count": 1, "is_parallel": true, "self": 0.02124975499464199 }, "steps_from_proto": { "total": 0.0020292629778850824, "count": 2, "is_parallel": true, "self": 0.0004114069161005318, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016178560617845505, "count": 8, "is_parallel": true, "self": 0.0016178560617845505 } } } } } } }, "steps_from_proto": { "total": 0.4603567080339417, "count": 500, "is_parallel": true, "self": 0.09795306270825677, "children": { "_process_rank_one_or_two_observation": { "total": 0.3624036453256849, "count": 2000, "is_parallel": true, "self": 0.3624036453256849 } } }, "UnityEnvironment.step": { "total": 30775.182656733872, "count": 3422861, "is_parallel": true, "self": 1669.3998983051279, "children": { "UnityEnvironment._generate_step_input": { "total": 1166.5835989805928, "count": 3422861, "is_parallel": true, "self": 1166.5835989805928 }, "communicator.exchange": { "total": 22646.438464231906, "count": 3422861, "is_parallel": true, "self": 22646.438464231906 }, "steps_from_proto": { "total": 5292.760695216246, "count": 6845722, "is_parallel": true, "self": 1138.2786801359034, "children": { "_process_rank_one_or_two_observation": { "total": 4154.4820150803425, "count": 27382888, "is_parallel": true, "self": 4154.4820150803425 } } } } } } } } } } }, "trainer_advance": { "total": 20220.885494026006, "count": 3422862, "self": 427.4996939775883, "children": { "process_trajectory": { "total": 7681.809909527277, "count": 3422862, "self": 7659.8104141058575, "children": { "RLTrainer._checkpoint": { "total": 21.99949542141985, "count": 100, "self": 21.99949542141985 } } }, "_update_policy": { "total": 12111.57589052114, "count": 2426, "self": 7725.115777124796, "children": { "TorchPOCAOptimizer.update": { "total": 4386.460113396344, "count": 72780, "self": 4386.460113396344 } } } } } } }, "trainer_threads": { "total": 1.167994923889637e-06, "count": 1, "self": 1.167994923889637e-06 }, "TrainerController._save_models": { "total": 0.21596961800241843, "count": 1, "self": 0.0015275460318662226, "children": { "RLTrainer._checkpoint": { "total": 0.2144420719705522, "count": 1, "self": 0.2144420719705522 } } } } } } }