{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.5860754251480103, "min": 0.5552442669868469, "max": 1.5035649538040161, "count": 7547 }, "SoccerTwos.Policy.Entropy.sum": { "value": 11665.2451171875, "min": 9538.4326171875, "max": 36082.8828125, "count": 7547 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.84782608695652, "min": 44.51376146788991, "max": 102.08, "count": 7547 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19080.0, "min": 14576.0, "max": 21716.0, "count": 7547 }, "SoccerTwos.Self-play.ELO.mean": { "value": 2020.0622900649475, "min": 1811.0887088074808, "max": 2064.0528990523876, "count": 7547 }, "SoccerTwos.Self-play.ELO.sum": { "value": 371691.46137195034, "min": 182914.6332417105, "max": 442594.2553746345, "count": 7547 }, "SoccerTwos.Step.mean": { "value": 99999997.0, "min": 24539921.0, "max": 99999997.0, "count": 7547 }, "SoccerTwos.Step.sum": { "value": 99999997.0, "min": 24539921.0, "max": 99999997.0, "count": 7547 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03841900825500488, "min": -0.12398265302181244, "max": 0.08097296208143234, "count": 7547 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.107516288757324, "min": -21.696964263916016, "max": 13.198593139648438, "count": 7547 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.038362208753824234, "min": -0.12447786331176758, "max": 0.08377066999673843, "count": 7547 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.09700870513916, "min": -21.783626556396484, "max": 13.654619216918945, "count": 7547 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 7547 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 7547 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.01118270190986427, "min": -0.432298111840614, "max": 0.39425536602903893, "count": 7547 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.06879985332489, "min": -68.73539978265762, "max": 69.78319978713989, "count": 7547 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.01118270190986427, "min": -0.432298111840614, "max": 0.39425536602903893, "count": 7547 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.06879985332489, "min": -68.73539978265762, "max": 69.78319978713989, "count": 7547 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7547 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7547 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01313792565924814, "min": 0.006748788067003867, "max": 0.018132517344201914, "count": 1837 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01313792565924814, "min": 0.006748788067003867, "max": 0.018132517344201914, "count": 1837 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10392129793763161, "min": 0.0829622300962607, "max": 0.12137279411156972, "count": 1837 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10392129793763161, "min": 0.0829622300962607, "max": 0.12137279411156972, "count": 1837 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10414750551184018, "min": 0.08385376607378324, "max": 0.12209492151935895, "count": 1837 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10414750551184018, "min": 0.08385376607378324, "max": 0.12209492151935895, "count": 1837 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 6.48999787000056e-09, "min": 6.48999787000056e-09, "max": 0.000226278738573762, "count": 1837 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 6.48999787000056e-09, "min": 6.48999787000056e-09, "max": 0.000226278738573762, "count": 1837 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10000213000000001, "min": 0.10000213000000001, "max": 0.175426238, "count": 1837 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10000213000000001, "min": 0.10000213000000001, "max": 0.175426238, "count": 1837 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.010628700000001e-05, "min": 1.010628700000001e-05, "max": 0.0037737692762000014, "count": 1837 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.010628700000001e-05, "min": 1.010628700000001e-05, "max": 0.0037737692762000014, "count": 1837 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711283121", "python_version": "3.10.1 (main, Mar 20 2024, 23:11:47) [Clang 15.0.0 (clang-1500.3.9.4)]", "command_line_arguments": "/Users/paul/.pyenv/versions/venv_unit5_hf/bin/mlagents-learn ./config/poca/SoccerTwos00.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos00 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1", "numpy_version": "1.23.5", "end_time_seconds": "1711528600" }, "total": 245477.12733966703, "count": 1, "self": 0.24398920801468194, "children": { "run_training.setup": { "total": 0.012441333994502202, "count": 1, "self": 0.012441333994502202 }, "TrainerController.start_learning": { "total": 245476.87090912502, "count": 1, "self": 48.019182801566785, "children": { "TrainerController._reset_env": { "total": 9.865059326170012, "count": 203, "self": 9.865059326170012 }, "TrainerController.advance": { "total": 245418.89493316427, "count": 5195544, "self": 41.95866535537061, "children": { "env_step": { "total": 200737.06311002214, "count": 5195544, "self": 194810.4156835102, "children": { "SubprocessEnvManager._take_step": { "total": 5897.157632466056, "count": 5195544, "self": 193.83796419762075, "children": { "TorchPolicy.evaluate": { "total": 5703.319668268436, "count": 9453636, "self": 5703.319668268436 } } }, "workers": { "total": 29.48979404589045, "count": 5195544, "self": 0.0, "children": { "worker_root": { "total": 245409.40406282153, "count": 5195544, "is_parallel": true, "self": 56015.21461811659, "children": { "steps_from_proto": { "total": 0.2706993741740007, "count": 406, "is_parallel": true, "self": 0.03438532294239849, "children": { "_process_rank_one_or_two_observation": { "total": 0.2363140512316022, "count": 1624, "is_parallel": true, "self": 0.2363140512316022 } } }, "UnityEnvironment.step": { "total": 189393.91874533077, "count": 5195544, "is_parallel": true, "self": 480.95873745632707, "children": { "UnityEnvironment._generate_step_input": { "total": 3459.8037157750805, "count": 5195544, "is_parallel": true, "self": 3459.8037157750805 }, "communicator.exchange": { "total": 179190.89349023328, "count": 5195544, "is_parallel": true, "self": 179190.89349023328 }, "steps_from_proto": { "total": 6262.262801866076, "count": 10391088, "is_parallel": true, "self": 769.0748052389536, "children": { "_process_rank_one_or_two_observation": { "total": 5493.187996627123, "count": 41564352, "is_parallel": true, "self": 5493.187996627123 } } } } } } } } } } }, "trainer_advance": { "total": 44639.87315778676, "count": 5195544, "self": 364.8762370394834, "children": { "process_trajectory": { "total": 7801.286456701375, "count": 5195544, "self": 7787.036999287549, "children": { "RLTrainer._checkpoint": { "total": 14.24945741382544, "count": 151, "self": 14.24945741382544 } } }, "_update_policy": { "total": 36473.7104640459, "count": 1837, "self": 4713.920209994394, "children": { "TorchPOCAOptimizer.update": { "total": 31759.790254051506, "count": 55110, "self": 31759.790254051506 } } } } } } }, "trainer_threads": { "total": 3.3300602808594704e-07, "count": 1, "self": 3.3300602808594704e-07 }, "TrainerController._save_models": { "total": 0.0917335000121966, "count": 1, "self": 0.0011219169828109443, "children": { "RLTrainer._checkpoint": { "total": 0.09061158302938566, "count": 1, "self": 0.09061158302938566 } } } } } } }