{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.209474802017212, "min": 3.1888222694396973, "max": 3.2957417964935303, "count": 64 }, "SoccerTwos.Policy.Entropy.sum": { "value": 73227.375, "min": 15208.412109375, "max": 106662.3984375, "count": 64 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 860.6666666666666, "min": 498.0, "max": 999.0, "count": 64 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20656.0, "min": 12220.0, "max": 26432.0, "count": 64 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1205.940405594161, "min": 1199.2562388766496, "max": 1207.7641443217108, "count": 48 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2411.880811188322, "min": 2398.512477753299, "max": 14405.181302303918, "count": 48 }, "SoccerTwos.Step.mean": { "value": 639300.0, "min": 9218.0, "max": 639300.0, "count": 64 }, "SoccerTwos.Step.sum": { "value": 639300.0, "min": 9218.0, "max": 639300.0, "count": 64 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.006309721153229475, "min": -0.013774292543530464, "max": 0.03452916443347931, "count": 64 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.06940693408250809, "min": -0.14126862585544586, "max": 0.553314208984375, "count": 64 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006794257089495659, "min": -0.01136896014213562, "max": 0.034900568425655365, "count": 64 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.0747368261218071, "min": -0.14779648184776306, "max": 0.5539351105690002, "count": 64 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 64 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 64 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.18181818181818182, "min": -0.46153846153846156, "max": 0.2861142892922674, "count": 64 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -6.0, "max": 4.0056000500917435, "count": 64 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.18181818181818182, "min": -0.46153846153846156, "max": 0.2861142892922674, "count": 64 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -6.0, "max": 4.0056000500917435, "count": 64 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 64 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 64 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018384612671798094, "min": 0.010855722728107746, "max": 0.02520257059659343, "count": 29 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018384612671798094, "min": 0.010855722728107746, "max": 0.02520257059659343, "count": 29 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0012903024636519453, "min": 3.3449284804495012e-06, "max": 0.004801920638419688, "count": 29 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0012903024636519453, "min": 3.3449284804495012e-06, "max": 0.004801920638419688, "count": 29 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0012918052981452397, "min": 3.429187124008119e-06, "max": 0.00484771333479633, "count": 29 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0012918052981452397, "min": 3.429187124008119e-06, "max": 0.00484771333479633, "count": 29 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 29 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 29 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 29 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 29 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 29 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 29 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724366390", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/poca/SoccerTwos_monti-python.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics --force", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1724367769" }, "total": 1378.3384690340026, "count": 1, "self": 0.21425851999083534, "children": { "run_training.setup": { "total": 0.01774524900247343, "count": 1, "self": 0.01774524900247343 }, "TrainerController.start_learning": { "total": 1378.1064652650093, "count": 1, "self": 0.8799141031340696, "children": { "TrainerController._reset_env": { "total": 4.761846583001898, "count": 4, "self": 4.761846583001898 }, "TrainerController.advance": { "total": 1372.1884267508576, "count": 42697, "self": 0.9978618613968138, "children": { "env_step": { "total": 1111.4932532657403, "count": 42697, "self": 702.9615276714903, "children": { "SubprocessEnvManager._take_step": { "total": 407.8746179653972, "count": 42697, "self": 6.701437480456661, "children": { "TorchPolicy.evaluate": { "total": 401.17318048494053, "count": 84773, "self": 401.17318048494053 } } }, "workers": { "total": 0.6571076288528275, "count": 42696, "self": 0.0, "children": { "worker_root": { "total": 1375.734532308139, "count": 42696, "is_parallel": true, "self": 777.0212588943687, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0038299079897115007, "count": 2, "is_parallel": true, "self": 0.0012818250252166763, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025480829644948244, "count": 8, "is_parallel": true, "self": 0.0025480829644948244 } } }, "UnityEnvironment.step": { "total": 0.14370961100212298, "count": 1, "is_parallel": true, "self": 0.0017833859892562032, "children": { "UnityEnvironment._generate_step_input": { "total": 0.008020116001716815, "count": 1, "is_parallel": true, "self": 0.008020116001716815 }, "communicator.exchange": { "total": 0.1266742670122767, "count": 1, "is_parallel": true, "self": 0.1266742670122767 }, "steps_from_proto": { "total": 0.0072318419988732785, "count": 2, "is_parallel": true, "self": 0.0031028410012368113, "children": { "_process_rank_one_or_two_observation": { "total": 0.004129000997636467, "count": 8, "is_parallel": true, "self": 0.004129000997636467 } } } } } } }, "UnityEnvironment.step": { "total": 598.7091519027599, "count": 42695, "is_parallel": true, "self": 19.94272614219517, "children": { "UnityEnvironment._generate_step_input": { "total": 12.824735618050909, "count": 42695, "is_parallel": true, "self": 12.824735618050909 }, "communicator.exchange": { "total": 503.6814929730899, "count": 42695, "is_parallel": true, "self": 503.6814929730899 }, "steps_from_proto": { "total": 62.26019716942392, "count": 85390, "is_parallel": true, "self": 13.469228172602016, "children": { "_process_rank_one_or_two_observation": { "total": 48.7909689968219, "count": 341560, "is_parallel": true, "self": 48.7909689968219 } } } } }, "steps_from_proto": { "total": 0.004121511010453105, "count": 6, "is_parallel": true, "self": 0.0009598119795555249, "children": { "_process_rank_one_or_two_observation": { "total": 0.00316169903089758, "count": 24, "is_parallel": true, "self": 0.00316169903089758 } } } } } } } } }, "trainer_advance": { "total": 259.69731162372045, "count": 42696, "self": 7.711557417947915, "children": { "process_trajectory": { "total": 92.47993407177273, "count": 42696, "self": 91.53840788676462, "children": { "RLTrainer._checkpoint": { "total": 0.9415261850081151, "count": 1, "self": 0.9415261850081151 } } }, "_update_policy": { "total": 159.5058201339998, "count": 30, "self": 88.51124684415117, "children": { "TorchPOCAOptimizer.update": { "total": 70.99457328984863, "count": 906, "self": 70.99457328984863 } } } } } } }, "trainer_threads": { "total": 1.167005393654108e-06, "count": 1, "self": 1.167005393654108e-06 }, "TrainerController._save_models": { "total": 0.27627666101034265, "count": 1, "self": 0.0014554330118699, "children": { "RLTrainer._checkpoint": { "total": 0.27482122799847275, "count": 1, "self": 0.27482122799847275 } } } } } } }