{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.101550817489624, "min": 2.0928046703338623, "max": 3.2957100868225098, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41493.01953125, "min": 26863.70703125, "max": 149262.984375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 48.54545454545455, "min": 40.601694915254235, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19224.0, "min": 15016.0, "max": 27340.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1509.5384765334704, "min": 1199.6849224996595, "max": 1509.5384765334704, "count": 455 }, "SoccerTwos.Self-play.ELO.sum": { "value": 298888.61835362716, "min": 2399.8665656259614, "max": 352915.36676651496, "count": 455 }, "SoccerTwos.Step.mean": { "value": 4999942.0, "min": 9688.0, "max": 4999942.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999942.0, "min": 9688.0, "max": 4999942.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04167698323726654, "min": -0.08756899833679199, "max": 0.17874084413051605, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 8.252042770385742, "min": -17.601367950439453, "max": 29.46053695678711, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.041709285229444504, "min": -0.091096431016922, "max": 0.18130771815776825, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.258438110351562, "min": -18.310382843017578, "max": 30.195301055908203, "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": 0.08331515150840836, "min": -0.5126210542297677, "max": 0.49391250126063824, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 16.496399998664856, "min": -46.68359994888306, "max": 55.72399973869324, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.08331515150840836, "min": -0.5126210542297677, "max": 0.49391250126063824, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 16.496399998664856, "min": -46.68359994888306, "max": 55.72399973869324, "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": 0.01637880486669019, "min": 0.010827948125855377, "max": 0.02561439787192891, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01637880486669019, "min": 0.010827948125855377, "max": 0.02561439787192891, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09951823924978574, "min": 1.838042171584675e-05, "max": 0.11822265212734541, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09951823924978574, "min": 1.838042171584675e-05, "max": 0.11822265212734541, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10291063313682874, "min": 1.8114200580991262e-05, "max": 0.12203358734647433, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10291063313682874, "min": 1.8114200580991262e-05, "max": 0.12203358734647433, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700139533", "python_version": "3.10.7 (tags/v3.10.7:6cc6b13, Sep 5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\lecom\\OneDrive\\Bureau\\unit7\\myenv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1700156926" }, "total": 17393.02601479995, "count": 1, "self": 2.814582899911329, "children": { "run_training.setup": { "total": 0.12561729992739856, "count": 1, "self": 0.12561729992739856 }, "TrainerController.start_learning": { "total": 17390.085814600112, "count": 1, "self": 9.584603649331257, "children": { "TrainerController._reset_env": { "total": 33.72335370001383, "count": 25, "self": 33.72335370001383 }, "TrainerController.advance": { "total": 17346.615686350735, "count": 335460, "self": 9.713295564521104, "children": { "env_step": { "total": 7467.404956086306, "count": 335460, "self": 5772.600437084911, "children": { "SubprocessEnvManager._take_step": { "total": 1688.5649934096728, "count": 335460, "self": 57.244869445450604, "children": { "TorchPolicy.evaluate": { "total": 1631.3201239642221, "count": 638264, "self": 1631.3201239642221 } } }, "workers": { "total": 6.239525591721758, "count": 335460, "self": 0.0, "children": { "worker_root": { "total": 17344.003261046717, "count": 335460, "is_parallel": true, "self": 12703.095018838532, "children": { "steps_from_proto": { "total": 0.0538211006205529, "count": 50, "is_parallel": true, "self": 0.010383699787780643, "children": { "_process_rank_one_or_two_observation": { "total": 0.043437400832772255, "count": 200, "is_parallel": true, "self": 0.043437400832772255 } } }, "UnityEnvironment.step": { "total": 4640.854421107564, "count": 335460, "is_parallel": true, "self": 253.85978173161857, "children": { "UnityEnvironment._generate_step_input": { "total": 197.41559677710757, "count": 335460, "is_parallel": true, "self": 197.41559677710757 }, "communicator.exchange": { "total": 3415.724447012879, "count": 335460, "is_parallel": true, "self": 3415.724447012879 }, "steps_from_proto": { "total": 773.854595585959, "count": 670920, "is_parallel": true, "self": 145.52071978128515, "children": { "_process_rank_one_or_two_observation": { "total": 628.3338758046739, "count": 2683680, "is_parallel": true, "self": 628.3338758046739 } } } } } } } } } } }, "trainer_advance": { "total": 9869.497434699908, "count": 335460, "self": 71.63206536625512, "children": { "process_trajectory": { "total": 1440.7136191353202, "count": 335460, "self": 1438.7640956351534, "children": { "RLTrainer._checkpoint": { "total": 1.9495235001668334, "count": 10, "self": 1.9495235001668334 } } }, "_update_policy": { "total": 8357.151750198333, "count": 237, "self": 798.1456429066602, "children": { "TorchPOCAOptimizer.update": { "total": 7559.006107291672, "count": 7110, "self": 7559.006107291672 } } } } } } }, "trainer_threads": { "total": 8.00006091594696e-07, "count": 1, "self": 8.00006091594696e-07 }, "TrainerController._save_models": { "total": 0.16217010002583265, "count": 1, "self": 0.011222600005567074, "children": { "RLTrainer._checkpoint": { "total": 0.15094750002026558, "count": 1, "self": 0.15094750002026558 } } } } } } }