{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4437261819839478, "min": 1.3191524744033813, "max": 3.2957499027252197, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28412.53125, "min": 18920.734375, "max": 149708.375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.35, "min": 41.05128205128205, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19632.0, "min": 15780.0, "max": 26252.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1530.675272893563, "min": 1188.3003152093995, "max": 1696.5585953519994, "count": 4983 }, "SoccerTwos.Self-play.ELO.sum": { "value": 244908.04366297007, "min": 2380.5804750961815, "max": 378388.3610630744, "count": 4983 }, "SoccerTwos.Step.mean": { "value": 49999986.0, "min": 9144.0, "max": 49999986.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999986.0, "min": 9144.0, "max": 49999986.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.027015339583158493, "min": -0.13505543768405914, "max": 0.178589329123497, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.322454452514648, "min": -23.531972885131836, "max": 31.459688186645508, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.029017603024840355, "min": -0.13433317840099335, "max": 0.16843070089817047, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.642816543579102, "min": -23.356122970581055, "max": 31.98929214477539, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.013792501389980316, "min": -0.7233818180181764, "max": 0.49086666603883106, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.2068002223968506, "min": -63.673599898815155, "max": 64.4132000207901, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.013792501389980316, "min": -0.7233818180181764, "max": 0.49086666603883106, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.2068002223968506, "min": -63.673599898815155, "max": 64.4132000207901, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01623503849065552, "min": 0.00989563539721227, "max": 0.02514854889983932, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01623503849065552, "min": 0.00989563539721227, "max": 0.02514854889983932, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1080243485669295, "min": 1.4108178038441111e-05, "max": 0.12073265686631203, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1080243485669295, "min": 1.4108178038441111e-05, "max": 0.12073265686631203, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10951551621158918, "min": 1.5877292601847632e-05, "max": 0.12368628233671189, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10951551621158918, "min": 1.5877292601847632e-05, "max": 0.12368628233671189, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706175863", "python_version": "3.10.13 (main, Aug 25 2023, 13:20:03) [GCC 9.4.0]", "command_line_arguments": "/home/master/data/playground-ai/huggingface-deepRLcourse-code/unit7/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=soccer-match-01 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706315785" }, "total": 139921.382584403, "count": 1, "self": 0.5813442880171351, "children": { "run_training.setup": { "total": 0.02423738999999614, "count": 1, "self": 0.02423738999999614 }, "TrainerController.start_learning": { "total": 139920.777002725, "count": 1, "self": 61.59774180309614, "children": { "TrainerController._reset_env": { "total": 6.716655895987174, "count": 250, "self": 6.716655895987174 }, "TrainerController.advance": { "total": 139852.3475367389, "count": 3441376, "self": 59.860270032368135, "children": { "env_step": { "total": 57460.43834806551, "count": 3441376, "self": 46387.08946334287, "children": { "SubprocessEnvManager._take_step": { "total": 11036.400403515316, "count": 3441376, "self": 390.2005497608079, "children": { "TorchPolicy.evaluate": { "total": 10646.199853754508, "count": 6280644, "self": 10646.199853754508 } } }, "workers": { "total": 36.9484812073278, "count": 3441376, "self": 0.0, "children": { "worker_root": { "total": 139809.41468983694, "count": 3441376, "is_parallel": true, "self": 100792.78921091175, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007985864000033871, "count": 2, "is_parallel": true, "self": 0.0038857830001006732, "children": { "_process_rank_one_or_two_observation": { "total": 0.004100080999933198, "count": 8, "is_parallel": true, "self": 0.004100080999933198 } } }, "UnityEnvironment.step": { "total": 0.02551318500002253, "count": 1, "is_parallel": true, "self": 0.0011131960000057006, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007367970000018431, "count": 1, "is_parallel": true, "self": 0.0007367970000018431 }, "communicator.exchange": { "total": 0.020698205999963193, "count": 1, "is_parallel": true, "self": 0.020698205999963193 }, "steps_from_proto": { "total": 0.0029649860000517947, "count": 2, "is_parallel": true, "self": 0.0004951960000312283, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024697900000205664, "count": 8, "is_parallel": true, "self": 0.0024697900000205664 } } } } } } }, "UnityEnvironment.step": { "total": 39016.23812165933, "count": 3441375, "is_parallel": true, "self": 2471.7688983174085, "children": { "UnityEnvironment._generate_step_input": { "total": 1858.1651202203038, "count": 3441375, "is_parallel": true, "self": 1858.1651202203038 }, "communicator.exchange": { "total": 27777.367676347036, "count": 3441375, "is_parallel": true, "self": 27777.367676347036 }, "steps_from_proto": { "total": 6908.936426774582, "count": 6882750, "is_parallel": true, "self": 1219.787076788617, "children": { "_process_rank_one_or_two_observation": { "total": 5689.149349985965, "count": 27531000, "is_parallel": true, "self": 5689.149349985965 } } } } }, "steps_from_proto": { "total": 0.3873572658640114, "count": 498, "is_parallel": true, "self": 0.07799724192591384, "children": { "_process_rank_one_or_two_observation": { "total": 0.3093600239380976, "count": 1992, "is_parallel": true, "self": 0.3093600239380976 } } } } } } } } }, "trainer_advance": { "total": 82332.04891864101, "count": 3441376, "self": 450.550804088678, "children": { "process_trajectory": { "total": 10232.844481900389, "count": 3441376, "self": 10220.917608415373, "children": { "RLTrainer._checkpoint": { "total": 11.926873485016358, "count": 100, "self": 11.926873485016358 } } }, "_update_policy": { "total": 71648.65363265194, "count": 2424, "self": 5406.411007832256, "children": { "TorchPOCAOptimizer.update": { "total": 66242.24262481969, "count": 72720, "self": 66242.24262481969 } } } } } } }, "trainer_threads": { "total": 7.00005330145359e-07, "count": 1, "self": 7.00005330145359e-07 }, "TrainerController._save_models": { "total": 0.1150675870012492, "count": 1, "self": 0.0019556840125005692, "children": { "RLTrainer._checkpoint": { "total": 0.11311190298874862, "count": 1, "self": 0.11311190298874862 } } } } } } }