{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6622945070266724, "min": 1.4777714014053345, "max": 2.3602654933929443, "count": 1792 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32660.76171875, "min": 26372.533203125, "max": 52087.3359375, "count": 1792 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.5774647887324, "min": 43.214285714285715, "max": 135.5142857142857, "count": 1792 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19760.0, "min": 11968.0, "max": 21432.0, "count": 1792 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1429.6834391114112, "min": 1267.8483300636103, "max": 1442.8017261441944, "count": 1792 }, "SoccerTwos.Self-play.ELO.sum": { "value": 203015.0483538204, "min": 90404.93167926311, "max": 304220.6827741176, "count": 1792 }, "SoccerTwos.Step.mean": { "value": 20109806.0, "min": 2199998.0, "max": 20109806.0, "count": 1792 }, "SoccerTwos.Step.sum": { "value": 20109806.0, "min": 2199998.0, "max": 20109806.0, "count": 1792 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04578428715467453, "min": -0.13799507915973663, "max": 0.09785564988851547, "count": 1792 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.501368522644043, "min": -26.63304901123047, "max": 17.735788345336914, "count": 1792 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04887549951672554, "min": -0.13961166143417358, "max": 0.09776446223258972, "count": 1792 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.94032096862793, "min": -26.945051193237305, "max": 17.878185272216797, "count": 1792 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1792 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1792 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.12329718176747712, "min": -0.41600384563207626, "max": 0.36480800008773806, "count": 1792 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -17.50819981098175, "min": -52.78160011768341, "max": 45.601000010967255, "count": 1792 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12329718176747712, "min": -0.41600384563207626, "max": 0.36480800008773806, "count": 1792 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -17.50819981098175, "min": -52.78160011768341, "max": 45.601000010967255, "count": 1792 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1792 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1792 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012768109767542531, "min": 0.010367057458400572, "max": 0.02548085546004586, "count": 869 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012768109767542531, "min": 0.010367057458400572, "max": 0.02548085546004586, "count": 869 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09177817876140276, "min": 0.05979832634329796, "max": 0.12440450837214788, "count": 869 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09177817876140276, "min": 0.05979832634329796, "max": 0.12440450837214788, "count": 869 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09319816902279854, "min": 0.061159982532262805, "max": 0.12736019790172576, "count": 869 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09319816902279854, "min": 0.061159982532262805, "max": 0.12736019790172576, "count": 869 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 869 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 869 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 869 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 869 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 869 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 869 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696277873", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\assia\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1696365061" }, "total": 87188.3295095, "count": 1, "self": 2.304758000012953, "children": { "run_training.setup": { "total": 0.11412949999999977, "count": 1, "self": 0.11412949999999977 }, "TrainerController.start_learning": { "total": 87185.910622, "count": 1, "self": 42.97262080095243, "children": { "TrainerController._reset_env": { "total": 11.842777299992319, "count": 359, "self": 11.842777299992319 }, "TrainerController.advance": { "total": 87130.83902779905, "count": 1249186, "self": 43.913307196169626, "children": { "env_step": { "total": 34529.831184197974, "count": 1249186, "self": 27557.149798199607, "children": { "SubprocessEnvManager._take_step": { "total": 6945.387012902138, "count": 1249186, "self": 221.06731429970478, "children": { "TorchPolicy.evaluate": { "total": 6724.319698602433, "count": 2277496, "self": 6724.319698602433 } } }, "workers": { "total": 27.29437309622666, "count": 1249186, "self": 0.0, "children": { "worker_root": { "total": 87058.09205769956, "count": 1249186, "is_parallel": true, "self": 64241.860530789745, "children": { "steps_from_proto": { "total": 0.9765216000583141, "count": 718, "is_parallel": true, "self": 0.18875550028448984, "children": { "_process_rank_one_or_two_observation": { "total": 0.7877660997738243, "count": 2872, "is_parallel": true, "self": 0.7877660997738243 } } }, "UnityEnvironment.step": { "total": 22815.25500530975, "count": 1249186, "is_parallel": true, "self": 1124.5716741985998, "children": { "UnityEnvironment._generate_step_input": { "total": 765.9207953082126, "count": 1249186, "is_parallel": true, "self": 765.9207953082126 }, "communicator.exchange": { "total": 17210.207485297262, "count": 1249186, "is_parallel": true, "self": 17210.207485297262 }, "steps_from_proto": { "total": 3714.555050505679, "count": 2498372, "is_parallel": true, "self": 720.1168485956996, "children": { "_process_rank_one_or_two_observation": { "total": 2994.4382019099794, "count": 9993488, "is_parallel": true, "self": 2994.4382019099794 } } } } } } } } } } }, "trainer_advance": { "total": 52557.094536404904, "count": 1249186, "self": 286.5318229020704, "children": { "process_trajectory": { "total": 6838.996242502752, "count": 1249186, "self": 6831.211235102757, "children": { "RLTrainer._checkpoint": { "total": 7.7850073999945835, "count": 36, "self": 7.7850073999945835 } } }, "_update_policy": { "total": 45431.56647100008, "count": 870, "self": 2983.052892099724, "children": { "TorchPOCAOptimizer.update": { "total": 42448.513578900354, "count": 26096, "self": 42448.513578900354 } } } } } } }, "trainer_threads": { "total": 1.3999961083754897e-06, "count": 1, "self": 1.3999961083754897e-06 }, "TrainerController._save_models": { "total": 0.2561947000067448, "count": 1, "self": 0.010259700007736683, "children": { "RLTrainer._checkpoint": { "total": 0.24593499999900814, "count": 1, "self": 0.24593499999900814 } } } } } } }