{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.132392168045044, "min": 2.7980947494506836, "max": 3.295198917388916, "count": 3000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 133414.84375, "min": 44148.27734375, "max": 197553.390625, "count": 3000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 981.5555555555555, "min": 384.2, "max": 999.0, "count": 3000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 35336.0, "min": 27500.0, "max": 35792.0, "count": 3000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1174.4800294470729, "min": 1152.334753477878, "max": 1217.6819534744825, "count": 2841 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4697.9201177882915, "min": 2308.7556965116414, "max": 36002.476069656, "count": 2841 }, "SoccerTwos.Step.mean": { "value": 47999800.0, "min": 15620.0, "max": 47999800.0, "count": 3000 }, "SoccerTwos.Step.sum": { "value": 47999800.0, "min": 15620.0, "max": 47999800.0, "count": 3000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003107416443526745, "min": -1.0953278541564941, "max": 0.0036058947443962097, "count": 3000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.05282608047127724, "min": -24.097213745117188, "max": 0.06888406723737717, "count": 3000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0031074194703251123, "min": -1.0989567041397095, "max": 0.0036059014964848757, "count": 3000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.052826132625341415, "min": -24.177047729492188, "max": 0.06888425350189209, "count": 3000 }, "SoccerTwos.Policy.RndBaselineEstimate.mean": { "value": 0.000444981997134164, "min": -0.000454334745882079, "max": 6.09859561920166, "count": 3000 }, "SoccerTwos.Policy.RndBaselineEstimate.sum": { "value": 0.007564694155007601, "min": -0.008632360026240349, "max": 153.53292846679688, "count": 3000 }, "SoccerTwos.Policy.RndValueEstimate.mean": { "value": 0.0004449794359970838, "min": -0.00045433553168550134, "max": 6.09859561920166, "count": 3000 }, "SoccerTwos.Policy.RndValueEstimate.sum": { "value": 0.007564650382846594, "min": -0.008632374927401543, "max": 153.53292846679688, "count": 3000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.29411764705882354, "min": -0.5893615392538217, "max": 0.3275750055909157, "count": 3000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.0, "min": -17.169999957084656, "max": 7.861800134181976, "count": 3000 }, "SoccerTwos.Policy.RndReward.mean": { "value": 0.02999024695771582, "min": 0.0011296469429393967, "max": 7076.9688083814535, "count": 3000 }, "SoccerTwos.Policy.RndReward.sum": { "value": 0.5098341982811689, "min": 0.023770103754941374, "max": 162770.28259277344, "count": 3000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.29411764705882354, "min": -0.5893615392538217, "max": 0.3275750055909157, "count": 3000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.0, "min": -17.169999957084656, "max": 7.861800134181976, "count": 3000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.034011427875763424, "min": 0.009482975578672873, "max": 0.35181839764118195, "count": 2021 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.034011427875763424, "min": 0.009482975578672873, "max": 0.35181839764118195, "count": 2021 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.000704554028440422, "min": 8.442825873607637e-09, "max": 454.2638854980469, "count": 2021 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.000704554028440422, "min": 8.442825873607637e-09, "max": 454.2638854980469, "count": 2021 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.000704554028440422, "min": 8.4428835867012e-09, "max": 506.7797037760417, "count": 2021 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.000704554028440422, "min": 8.4428835867012e-09, "max": 506.7797037760417, "count": 2021 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 2021 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 2021 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10001708333333335, "min": 0.10001708333333335, "max": 0.19994972083333332, "count": 2021 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10001708333333335, "min": 0.10001708333333335, "max": 0.19994972083333332, "count": 2021 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.170662500000009e-05, "min": 1.170662500000009e-05, "max": 0.00999497711125, "count": 2021 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.170662500000009e-05, "min": 1.170662500000009e-05, "max": 0.00999497711125, "count": 2021 }, "SoccerTwos.Losses.RNDLoss.mean": { "value": 3.44461077474989e-05, "min": 1.9040650158785866e-06, "max": 7.383045196533203, "count": 2021 }, "SoccerTwos.Losses.RNDLoss.sum": { "value": 3.44461077474989e-05, "min": 1.9040650158785866e-06, "max": 7.383045196533203, "count": 2021 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676207748", "python_version": "3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]", "command_line_arguments": "/home/deep-rl/.local/bin/mlagents-learn config/poca/SoccerTwos.yaml --env training-envs-executables/SoccerTwos.x86_64 --run-id SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1676251229" }, "total": 43481.009814282006, "count": 1, "self": 0.21904235598049127, "children": { "run_training.setup": { "total": 0.010040364009910263, "count": 1, "self": 0.010040364009910263 }, "TrainerController.start_learning": { "total": 43480.780731562016, "count": 1, "self": 33.42600047615997, "children": { "TrainerController._reset_env": { "total": 7.4349382660439005, "count": 100, "self": 7.4349382660439005 }, "TrainerController.advance": { "total": 43439.807582472844, "count": 3062924, "self": 34.19506235700101, "children": { "env_step": { "total": 32537.51252939491, "count": 3062924, "self": 23571.234687711403, "children": { "SubprocessEnvManager._take_step": { "total": 8946.558222052365, "count": 3062924, "self": 304.98570815504354, "children": { "TorchPolicy.evaluate": { "total": 8641.572513897321, "count": 6078558, "self": 8641.572513897321 } } }, "workers": { "total": 19.71961963114154, "count": 3062924, "self": 0.0, "children": { "worker_root": { "total": 43436.64464662739, "count": 3062924, "is_parallel": true, "self": 24517.900909940072, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012339909881120548, "count": 2, "is_parallel": true, "self": 0.00030800099193584174, "children": { "_process_rank_one_or_two_observation": { "total": 0.000925989996176213, "count": 8, "is_parallel": true, "self": 0.000925989996176213 } } }, "UnityEnvironment.step": { "total": 0.021953343006316572, "count": 1, "is_parallel": true, "self": 0.0003455630212556571, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006698079960187897, "count": 1, "is_parallel": true, "self": 0.0006698079960187897 }, "communicator.exchange": { "total": 0.019872214004863054, "count": 1, "is_parallel": true, "self": 0.019872214004863054 }, "steps_from_proto": { "total": 0.001065757984179072, "count": 2, "is_parallel": true, "self": 0.00024018595286179334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008255720313172787, "count": 8, "is_parallel": true, "self": 0.0008255720313172787 } } } } } } }, "UnityEnvironment.step": { "total": 18918.64843232333, "count": 3062923, "is_parallel": true, "self": 986.5479166106816, "children": { "UnityEnvironment._generate_step_input": { "total": 712.3963567089668, "count": 3062923, "is_parallel": true, "self": 712.3963567089668 }, "communicator.exchange": { "total": 14332.539664651806, "count": 3062923, "is_parallel": true, "self": 14332.539664651806 }, "steps_from_proto": { "total": 2887.164494351877, "count": 6125846, "is_parallel": true, "self": 557.0796193042625, "children": { "_process_rank_one_or_two_observation": { "total": 2330.0848750476143, "count": 24503384, "is_parallel": true, "self": 2330.0848750476143 } } } } }, "steps_from_proto": { "total": 0.09530436398927122, "count": 198, "is_parallel": true, "self": 0.01923620468005538, "children": { "_process_rank_one_or_two_observation": { "total": 0.07606815930921584, "count": 792, "is_parallel": true, "self": 0.07606815930921584 } } } } } } } } }, "trainer_advance": { "total": 10868.099990720933, "count": 3062924, "self": 352.59623967079096, "children": { "process_trajectory": { "total": 5000.804463582928, "count": 3062924, "self": 4928.107200435916, "children": { "RLTrainer._checkpoint": { "total": 72.69726314701256, "count": 600, "self": 72.69726314701256 } } }, "_update_policy": { "total": 5514.699287467214, "count": 2021, "self": 1327.569331967592, "children": { "TorchPOCAOptimizer.update": { "total": 4187.129955499622, "count": 24252, "self": 4187.129955499622 } } } } } } }, "trainer_threads": { "total": 5.629844963550568e-07, "count": 1, "self": 5.629844963550568e-07 }, "TrainerController._save_models": { "total": 0.11220978398341686, "count": 1, "self": 0.0014431489689741284, "children": { "RLTrainer._checkpoint": { "total": 0.11076663501444273, "count": 1, "self": 0.11076663501444273 } } } } } } }