{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.5705924034118652, "min": 2.5705924034118652, "max": 2.733187437057495, "count": 9 }, "SoccerTwos.Policy.Entropy.sum": { "value": 82258.953125, "min": 82258.953125, "max": 87462.0, "count": 9 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 998.0, "max": 999.0, "count": 9 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 31968.0, "min": 31936.0, "max": 31968.0, "count": 9 }, "SoccerTwos.Step.mean": { "value": 4789068.0, "min": 4659078.0, "max": 4789068.0, "count": 14 }, "SoccerTwos.Step.sum": { "value": 4789068.0, "min": 4659078.0, "max": 4789068.0, "count": 14 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 8.117820107145235e-05, "min": 7.954680040711537e-05, "max": 0.0001631923660170287, "count": 14 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0008117820252664387, "min": 0.0007954679895192385, "max": 0.0016319237183779478, "count": 14 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 3.339347676956095e-05, "min": 3.339347676956095e-05, "max": 0.00011998324043815956, "count": 14 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.00033393476041965187, "min": 0.00033393476041965187, "max": 0.0011998324189335108, "count": 14 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 14 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 14 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 14 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 14 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 14 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 14 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018493434123229235, "min": 0.016156502508480722, "max": 0.01926012553093541, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018493434123229235, "min": 0.016156502508480722, "max": 0.01926012553093541, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.376311546705564e-08, "min": 1.376311546705564e-08, "max": 1.989213526738038e-08, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.376311546705564e-08, "min": 1.376311546705564e-08, "max": 1.989213526738038e-08, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.6120228786399415e-08, "min": 1.6120228786399415e-08, "max": 2.2838340759297657e-08, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.6120228786399415e-08, "min": 1.6120228786399415e-08, "max": 2.2838340759297657e-08, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.19999999999999993, "max": 0.19999999999999993, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1734663163", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./train-soccer/SoccerTwos.yaml --env=train-soccer/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwosNew --no-graphics --resume --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734664014" }, "total": 851.0100534910016, "count": 1, "self": 0.5337031950002711, "children": { "run_training.setup": { "total": 0.10962242599998717, "count": 1, "self": 0.10962242599998717 }, "TrainerController.start_learning": { "total": 850.3667278700013, "count": 1, "self": 0.3641235869436059, "children": { "TrainerController._reset_env": { "total": 3.136154830997839, "count": 2, "self": 3.136154830997839 }, "TrainerController.advance": { "total": 846.865701746061, "count": 9457, "self": 0.4272281033299805, "children": { "env_step": { "total": 337.8002917907979, "count": 9457, "self": 273.6974104630499, "children": { "SubprocessEnvManager._take_step": { "total": 63.88627816988446, "count": 9457, "self": 2.30563188585802, "children": { "TorchPolicy.evaluate": { "total": 61.58064628402644, "count": 18896, "self": 61.58064628402644 } } }, "workers": { "total": 0.21660315786357387, "count": 9456, "self": 0.0, "children": { "worker_root": { "total": 849.0394703048623, "count": 9456, "is_parallel": true, "self": 620.9276337478514, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004820147001737496, "count": 2, "is_parallel": true, "self": 0.0011661690114124212, "children": { "_process_rank_one_or_two_observation": { "total": 0.0036539779903250746, "count": 8, "is_parallel": true, "self": 0.0036539779903250746 } } }, "UnityEnvironment.step": { "total": 0.05040170900247176, "count": 1, "is_parallel": true, "self": 0.001424563004547963, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009843420011748094, "count": 1, "is_parallel": true, "self": 0.0009843420011748094 }, "communicator.exchange": { "total": 0.043613315996481106, "count": 1, "is_parallel": true, "self": 0.043613315996481106 }, "steps_from_proto": { "total": 0.004379488000267884, "count": 2, "is_parallel": true, "self": 0.0007522070009144954, "children": { "_process_rank_one_or_two_observation": { "total": 0.0036272809993533883, "count": 8, "is_parallel": true, "self": 0.0036272809993533883 } } } } } } }, "steps_from_proto": { "total": 0.002439471998513909, "count": 2, "is_parallel": true, "self": 0.0005652149993693456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018742569991445635, "count": 8, "is_parallel": true, "self": 0.0018742569991445635 } } }, "UnityEnvironment.step": { "total": 228.10939708501246, "count": 9455, "is_parallel": true, "self": 13.83459486391439, "children": { "UnityEnvironment._generate_step_input": { "total": 9.056584429068607, "count": 9455, "is_parallel": true, "self": 9.056584429068607 }, "communicator.exchange": { "total": 163.31950518598387, "count": 9455, "is_parallel": true, "self": 163.31950518598387 }, "steps_from_proto": { "total": 41.89871260604559, "count": 18910, "is_parallel": true, "self": 7.3057654969416035, "children": { "_process_rank_one_or_two_observation": { "total": 34.59294710910399, "count": 75640, "is_parallel": true, "self": 34.59294710910399 } } } } } } } } } } }, "trainer_advance": { "total": 508.63818185193304, "count": 9456, "self": 2.0362858940170554, "children": { "process_trajectory": { "total": 62.12042911892058, "count": 9456, "self": 62.12042911892058 }, "_update_policy": { "total": 444.4814668389954, "count": 4, "self": 28.49655190294652, "children": { "TorchPOCAOptimizer.update": { "total": 415.9849149360489, "count": 180, "self": 415.9849149360489 } } } } } } }, "trainer_threads": { "total": 1.6149970178958029e-06, "count": 1, "self": 1.6149970178958029e-06 }, "TrainerController._save_models": { "total": 0.0007460910019290168, "count": 1, "self": 7.261100108735263e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0006734800008416642, "count": 1, "self": 0.0006734800008416642 } } } } } } }