{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7809149026870728, "min": 1.7258027791976929, "max": 3.295712471008301, "count": 676 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34421.5234375, "min": 19026.62890625, "max": 111146.296875, "count": 676 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.528301886792455, "min": 38.110236220472444, "max": 999.0, "count": 676 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19728.0, "min": 14532.0, "max": 27812.0, "count": 676 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1546.1583655500951, "min": 1197.674072253018, "max": 1559.373964110729, "count": 667 }, "SoccerTwos.Self-play.ELO.sum": { "value": 327785.57349662017, "min": 2395.348144506036, "max": 380382.98396793095, "count": 667 }, "SoccerTwos.Step.mean": { "value": 6759994.0, "min": 9922.0, "max": 6759994.0, "count": 676 }, "SoccerTwos.Step.sum": { "value": 6759994.0, "min": 9922.0, "max": 6759994.0, "count": 676 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05039449781179428, "min": -0.12812939286231995, "max": 0.13954395055770874, "count": 676 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.633238792419434, "min": -23.59006118774414, "max": 22.925369262695312, "count": 676 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.048979852348566055, "min": -0.12161581963300705, "max": 0.1427195519208908, "count": 676 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.334749221801758, "min": -22.27959632873535, "max": 22.355365753173828, "count": 676 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 676 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 676 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.19450900452961853, "min": -0.5804499983787537, "max": 0.46777999997138975, "count": 676 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -41.04139995574951, "min": -55.459999799728394, "max": 50.888399720191956, "count": 676 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.19450900452961853, "min": -0.5804499983787537, "max": 0.46777999997138975, "count": 676 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -41.04139995574951, "min": -55.459999799728394, "max": 50.888399720191956, "count": 676 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 676 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 676 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020284115670559308, "min": 0.0111350942015027, "max": 0.02531395632152756, "count": 326 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020284115670559308, "min": 0.0111350942015027, "max": 0.02531395632152756, "count": 326 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11815406481424967, "min": 1.1465595531317927e-05, "max": 0.12800546834866205, "count": 326 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11815406481424967, "min": 1.1465595531317927e-05, "max": 0.12800546834866205, "count": 326 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.119600277642409, "min": 1.2429546269700179e-05, "max": 0.1303256573776404, "count": 326 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.119600277642409, "min": 1.2429546269700179e-05, "max": 0.1303256573776404, "count": 326 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 326 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 326 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 326 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 326 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 326 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 326 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698758718", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/loris/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu117", "numpy_version": "1.23.5", "end_time_seconds": "1698764424" }, "total": 5706.621346769001, "count": 1, "self": 0.08893190000162576, "children": { "run_training.setup": { "total": 0.009767644000021392, "count": 1, "self": 0.009767644000021392 }, "TrainerController.start_learning": { "total": 5706.522647225, "count": 1, "self": 5.924937289886657, "children": { "TrainerController._reset_env": { "total": 1.847396195998499, "count": 34, "self": 1.847396195998499 }, "TrainerController.advance": { "total": 5698.672009086115, "count": 466832, "self": 5.84066097311279, "children": { "env_step": { "total": 4304.882862541857, "count": 466832, "self": 3284.06622609237, "children": { "SubprocessEnvManager._take_step": { "total": 1017.2349912601608, "count": 466832, "self": 35.81308714550414, "children": { "TorchPolicy.evaluate": { "total": 981.4219041146566, "count": 851017, "self": 981.4219041146566 } } }, "workers": { "total": 3.5816451893265366, "count": 466831, "self": 0.0, "children": { "worker_root": { "total": 5698.93553781256, "count": 466831, "is_parallel": true, "self": 3065.1170296588193, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018119219998879998, "count": 2, "is_parallel": true, "self": 0.00044821299979957985, "children": { "_process_rank_one_or_two_observation": { "total": 0.00136370900008842, "count": 8, "is_parallel": true, "self": 0.00136370900008842 } } }, "UnityEnvironment.step": { "total": 0.012116857999899366, "count": 1, "is_parallel": true, "self": 0.0002898419998018653, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021020799977122806, "count": 1, "is_parallel": true, "self": 0.00021020799977122806 }, "communicator.exchange": { "total": 0.01082476100009444, "count": 1, "is_parallel": true, "self": 0.01082476100009444 }, "steps_from_proto": { "total": 0.0007920470002318325, "count": 2, "is_parallel": true, "self": 0.00015755899948999286, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006344880007418396, "count": 8, "is_parallel": true, "self": 0.0006344880007418396 } } } } } } }, "UnityEnvironment.step": { "total": 2633.7929615657454, "count": 466830, "is_parallel": true, "self": 144.23465086849137, "children": { "UnityEnvironment._generate_step_input": { "total": 82.530094460501, "count": 466830, "is_parallel": true, "self": 82.530094460501 }, "communicator.exchange": { "total": 2016.3691967651735, "count": 466830, "is_parallel": true, "self": 2016.3691967651735 }, "steps_from_proto": { "total": 390.65901947157954, "count": 933660, "is_parallel": true, "self": 73.53245093436863, "children": { "_process_rank_one_or_two_observation": { "total": 317.1265685372109, "count": 3734640, "is_parallel": true, "self": 317.1265685372109 } } } } }, "steps_from_proto": { "total": 0.025546587995449954, "count": 66, "is_parallel": true, "self": 0.005225847999554389, "children": { "_process_rank_one_or_two_observation": { "total": 0.020320739995895565, "count": 264, "is_parallel": true, "self": 0.020320739995895565 } } } } } } } } }, "trainer_advance": { "total": 1387.9484855711457, "count": 466831, "self": 41.307249054396834, "children": { "process_trajectory": { "total": 549.9510260567513, "count": 466831, "self": 548.7462396517508, "children": { "RLTrainer._checkpoint": { "total": 1.2047864050005046, "count": 13, "self": 1.2047864050005046 } } }, "_update_policy": { "total": 796.6902104599976, "count": 326, "self": 422.1617266649687, "children": { "TorchPOCAOptimizer.update": { "total": 374.52848379502893, "count": 9783, "self": 374.52848379502893 } } } } } } }, "trainer_threads": { "total": 6.40999132883735e-07, "count": 1, "self": 6.40999132883735e-07 }, "TrainerController._save_models": { "total": 0.07830401200044435, "count": 1, "self": 0.0008399329999519978, "children": { "RLTrainer._checkpoint": { "total": 0.07746407900049235, "count": 1, "self": 0.07746407900049235 } } } } } } }