{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.847357988357544, "min": 1.8039144277572632, "max": 3.2957615852355957, "count": 643 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36533.3515625, "min": 13936.708984375, "max": 129445.9765625, "count": 643 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.620253164556964, "min": 41.279661016949156, "max": 999.0, "count": 643 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19788.0, "min": 12412.0, "max": 29196.0, "count": 643 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1594.615008064832, "min": 1171.09056039849, "max": 1611.076103789316, "count": 587 }, "SoccerTwos.Self-play.ELO.sum": { "value": 251949.17127424345, "min": 2342.18112079698, "max": 371587.3148275218, "count": 587 }, "SoccerTwos.Step.mean": { "value": 6429966.0, "min": 9614.0, "max": 6429966.0, "count": 643 }, "SoccerTwos.Step.sum": { "value": 6429966.0, "min": 9614.0, "max": 6429966.0, "count": 643 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.029824908822774887, "min": -0.08514673262834549, "max": 0.1940293163061142, "count": 643 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.712335586547852, "min": -16.979042053222656, "max": 28.993396759033203, "count": 643 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02964496612548828, "min": -0.08863995969295502, "max": 0.19637098908424377, "count": 643 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.683904647827148, "min": -17.955656051635742, "max": 29.506513595581055, "count": 643 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 643 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 643 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.21634936709947225, "min": -0.6153846153846154, "max": 0.4518156881425895, "count": 643 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -34.183200001716614, "min": -47.33100003004074, "max": 72.88959991931915, "count": 643 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.21634936709947225, "min": -0.6153846153846154, "max": 0.4518156881425895, "count": 643 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -34.183200001716614, "min": -47.33100003004074, "max": 72.88959991931915, "count": 643 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 643 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 643 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0180307745715254, "min": 0.010349092696560546, "max": 0.021931897252216004, "count": 307 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0180307745715254, "min": 0.010349092696560546, "max": 0.021931897252216004, "count": 307 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11718054562807083, "min": 2.3144507821371008e-07, "max": 0.12711331248283386, "count": 307 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11718054562807083, "min": 2.3144507821371008e-07, "max": 0.12711331248283386, "count": 307 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1189131701985995, "min": 2.6177915941616446e-07, "max": 0.12865767553448676, "count": 307 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1189131701985995, "min": 2.6177915941616446e-07, "max": 0.12865767553448676, "count": 307 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 307 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 307 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 307 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 307 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 307 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 307 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696445858", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\vivin\\Anaconda3\\envs\\hfrl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1696530297" }, "total": 84443.6438798, "count": 1, "self": 2.986561099998653, "children": { "run_training.setup": { "total": 0.1693769999999999, "count": 1, "self": 0.1693769999999999 }, "TrainerController.start_learning": { "total": 84440.4879417, "count": 1, "self": 15.064017405602499, "children": { "TrainerController._reset_env": { "total": 5.9058642999637625, "count": 33, "self": 5.9058642999637625 }, "TrainerController.advance": { "total": 84419.28877399444, "count": 434518, "self": 15.178462592259166, "children": { "env_step": { "total": 10781.812579299307, "count": 434518, "self": 7998.074253597756, "children": { "SubprocessEnvManager._take_step": { "total": 2774.2928609035, "count": 434518, "self": 93.24658060185993, "children": { "TorchPolicy.evaluate": { "total": 2681.04628030164, "count": 816594, "self": 2681.04628030164 } } }, "workers": { "total": 9.445464798050937, "count": 434518, "self": 0.0, "children": { "worker_root": { "total": 84415.55031200343, "count": 434518, "is_parallel": true, "self": 78125.50294890224, "children": { "steps_from_proto": { "total": 0.1131358000279068, "count": 66, "is_parallel": true, "self": 0.021666400003675257, "children": { "_process_rank_one_or_two_observation": { "total": 0.09146940002423154, "count": 264, "is_parallel": true, "self": 0.09146940002423154 } } }, "UnityEnvironment.step": { "total": 6289.934227301162, "count": 434518, "is_parallel": true, "self": 392.26629980469625, "children": { "UnityEnvironment._generate_step_input": { "total": 317.1448525998336, "count": 434518, "is_parallel": true, "self": 317.1448525998336 }, "communicator.exchange": { "total": 4357.267293398496, "count": 434518, "is_parallel": true, "self": 4357.267293398496 }, "steps_from_proto": { "total": 1223.2557814981355, "count": 869036, "is_parallel": true, "self": 241.211575695977, "children": { "_process_rank_one_or_two_observation": { "total": 982.0442058021586, "count": 3476144, "is_parallel": true, "self": 982.0442058021586 } } } } } } } } } } }, "trainer_advance": { "total": 73622.29773210287, "count": 434518, "self": 103.21380430168938, "children": { "process_trajectory": { "total": 2728.664671401102, "count": 434518, "self": 2725.696154101119, "children": { "RLTrainer._checkpoint": { "total": 2.9685172999829774, "count": 12, "self": 2.9685172999829774 } } }, "_update_policy": { "total": 70790.41925640008, "count": 307, "self": 12139.413613700468, "children": { "TorchPOCAOptimizer.update": { "total": 58651.005642699616, "count": 9213, "self": 58651.005642699616 } } } } } } }, "trainer_threads": { "total": 2.0000006770715117e-06, "count": 1, "self": 2.0000006770715117e-06 }, "TrainerController._save_models": { "total": 0.22928400000091642, "count": 1, "self": 0.010616599989589304, "children": { "RLTrainer._checkpoint": { "total": 0.21866740001132712, "count": 1, "self": 0.21866740001132712 } } } } } } }