{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5368013381958008, "min": 1.4798517227172852, "max": 1.717839002609253, "count": 1387 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30391.783203125, "min": 26218.884765625, "max": 39726.2421875, "count": 1387 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 77.85714285714286, "min": 37.12977099236641, "max": 93.54716981132076, "count": 1387 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19620.0, "min": 18048.0, "max": 21044.0, "count": 1387 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1754.3647881834338, "min": 1663.1415280356007, "max": 1790.4749953370062, "count": 1387 }, "SoccerTwos.Self-play.ELO.sum": { "value": 221049.96331111266, "min": 186001.52819740935, "max": 454293.69494184444, "count": 1387 }, "SoccerTwos.Step.mean": { "value": 23799980.0, "min": 9939999.0, "max": 23799980.0, "count": 1387 }, "SoccerTwos.Step.sum": { "value": 23799980.0, "min": 9939999.0, "max": 23799980.0, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05803244933485985, "min": -0.15242762863636017, "max": 0.11841320246458054, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.370121002197266, "min": -25.455413818359375, "max": 21.788028717041016, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05722297355532646, "min": -0.1545315533876419, "max": 0.12288798391819, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.267317771911621, "min": -25.80677032470703, "max": 22.61138916015625, "count": 1387 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1387 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10333070839483907, "min": -0.4309287514537573, "max": 0.2959999988792808, "count": 1387 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.122999966144562, "min": -68.94860023260117, "max": 52.48499971628189, "count": 1387 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10333070839483907, "min": -0.4309287514537573, "max": 0.2959999988792808, "count": 1387 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.122999966144562, "min": -68.94860023260117, "max": 52.48499971628189, "count": 1387 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1387 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1387 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0157304969499819, "min": 0.01113445025572825, "max": 0.023960910368865978, "count": 673 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0157304969499819, "min": 0.01113445025572825, "max": 0.023960910368865978, "count": 673 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09982962533831596, "min": 0.08123996083935102, "max": 0.13158326968550682, "count": 673 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09982962533831596, "min": 0.08123996083935102, "max": 0.13158326968550682, "count": 673 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10118018761277199, "min": 0.08227557465434074, "max": 0.13501238425572712, "count": 673 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10118018761277199, "min": 0.08227557465434074, "max": 0.13501238425572712, "count": 673 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 673 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 673 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 673 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 673 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 673 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 673 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700170035", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Nicolas\\AppData\\Local\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "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": "1700206030" }, "total": 35995.33808009999, "count": 1, "self": 0.22053069998219144, "children": { "run_training.setup": { "total": 0.10423989999981131, "count": 1, "self": 0.10423989999981131 }, "TrainerController.start_learning": { "total": 35995.013309500006, "count": 1, "self": 25.657995370667777, "children": { "TrainerController._reset_env": { "total": 8.357257200070308, "count": 71, "self": 8.357257200070308 }, "TrainerController.advance": { "total": 35960.76777922927, "count": 963579, "self": 23.942669511641725, "children": { "env_step": { "total": 15560.645170511954, "count": 963579, "self": 12223.690495495524, "children": { "SubprocessEnvManager._take_step": { "total": 3321.942329308251, "count": 963579, "self": 122.52573752241733, "children": { "TorchPolicy.evaluate": { "total": 3199.4165917858336, "count": 1741048, "self": 3199.4165917858336 } } }, "workers": { "total": 15.012345708179055, "count": 963579, "self": 0.0, "children": { "worker_root": { "total": 35957.90660739917, "count": 963579, "is_parallel": true, "self": 26310.496169595644, "children": { "steps_from_proto": { "total": 0.1260338000865886, "count": 142, "is_parallel": true, "self": 0.025274900341173634, "children": { "_process_rank_one_or_two_observation": { "total": 0.10075889974541496, "count": 568, "is_parallel": true, "self": 0.10075889974541496 } } }, "UnityEnvironment.step": { "total": 9647.28440400344, "count": 963579, "is_parallel": true, "self": 481.2311691270734, "children": { "UnityEnvironment._generate_step_input": { "total": 444.0392231961887, "count": 963579, "is_parallel": true, "self": 444.0392231961887 }, "communicator.exchange": { "total": 7130.5163158940995, "count": 963579, "is_parallel": true, "self": 7130.5163158940995 }, "steps_from_proto": { "total": 1591.497695786078, "count": 1927158, "is_parallel": true, "self": 324.25971953383123, "children": { "_process_rank_one_or_two_observation": { "total": 1267.2379762522469, "count": 7708632, "is_parallel": true, "self": 1267.2379762522469 } } } } } } } } } } }, "trainer_advance": { "total": 20376.17993920567, "count": 963578, "self": 177.7759565134911, "children": { "process_trajectory": { "total": 3911.5704576928692, "count": 963578, "self": 3907.8274015928328, "children": { "RLTrainer._checkpoint": { "total": 3.7430561000364833, "count": 28, "self": 3.7430561000364833 } } }, "_update_policy": { "total": 16286.83352499931, "count": 673, "self": 2000.1610075011122, "children": { "TorchPOCAOptimizer.update": { "total": 14286.672517498198, "count": 20190, "self": 14286.672517498198 } } } } } } }, "trainer_threads": { "total": 4.3000036384910345e-06, "count": 1, "self": 4.3000036384910345e-06 }, "TrainerController._save_models": { "total": 0.23027339999680407, "count": 1, "self": 0.012849499995354563, "children": { "RLTrainer._checkpoint": { "total": 0.2174239000014495, "count": 1, "self": 0.2174239000014495 } } } } } } }