{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9657366871833801, "min": 0.9657366871833801, "max": 2.8535759449005127, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9858.240234375, "min": 9650.7861328125, "max": 29129.302734375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.26156997680664, "min": 0.45697101950645447, "max": 13.26156997680664, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2586.006103515625, "min": 87.73843383789062, "max": 2685.4189453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07049010705060366, "min": 0.06424208369040285, "max": 0.07244245190927803, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2819604282024146, "min": 0.2569683347616114, "max": 0.3622122595463902, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24469861512382823, "min": 0.20273444102620525, "max": 0.39705155190883895, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9787944604953129, "min": 0.810937764104821, "max": 1.845633884270986, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6300097370000015e-05, "min": 2.6300097370000015e-05, "max": 0.0009723000027699999, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00010520038948000006, "min": 0.00010520038948000006, "max": 0.0046140000386, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10210400000000001, "min": 0.10210400000000001, "max": 0.17778399999999997, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40841600000000006, "min": 0.40841600000000006, "max": 0.86912, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014123700000000008, "min": 0.00014123700000000008, "max": 0.004861776999999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005649480000000003, "min": 0.0005649480000000003, "max": 0.023073859999999995, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.84090909090909, "min": 4.0, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 176.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 4.0, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 176.0, "max": 1413.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1730781868", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730782371" }, "total": 502.95999253599996, "count": 1, "self": 0.4402316890000293, "children": { "run_training.setup": { "total": 0.0633147439999675, "count": 1, "self": 0.0633147439999675 }, "TrainerController.start_learning": { "total": 502.45644610299996, "count": 1, "self": 0.4445313880003141, "children": { "TrainerController._reset_env": { "total": 2.093534280999961, "count": 1, "self": 2.093534280999961 }, "TrainerController.advance": { "total": 499.81893255399984, "count": 18192, "self": 0.4637704620157592, "children": { "env_step": { "total": 355.03806629997905, "count": 18192, "self": 270.95680984998637, "children": { "SubprocessEnvManager._take_step": { "total": 83.81278630899328, "count": 18192, "self": 1.5013370629917517, "children": { "TorchPolicy.evaluate": { "total": 82.31144924600153, "count": 18192, "self": 82.31144924600153 } } }, "workers": { "total": 0.2684701409993977, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 500.8835530110025, "count": 18192, "is_parallel": true, "self": 263.8773119809972, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024018820000719643, "count": 1, "is_parallel": true, "self": 0.0007150510000428767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016868310000290876, "count": 10, "is_parallel": true, "self": 0.0016868310000290876 } } }, "UnityEnvironment.step": { "total": 0.04392610100001093, "count": 1, "is_parallel": true, "self": 0.0007495879999623867, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004451410000001488, "count": 1, "is_parallel": true, "self": 0.0004451410000001488 }, "communicator.exchange": { "total": 0.040123311000002104, "count": 1, "is_parallel": true, "self": 0.040123311000002104 }, "steps_from_proto": { "total": 0.002608061000046291, "count": 1, "is_parallel": true, "self": 0.00046605199975147116, "children": { "_process_rank_one_or_two_observation": { "total": 0.00214200900029482, "count": 10, "is_parallel": true, "self": 0.00214200900029482 } } } } } } }, "UnityEnvironment.step": { "total": 237.0062410300053, "count": 18191, "is_parallel": true, "self": 11.280102595008202, "children": { "UnityEnvironment._generate_step_input": { "total": 6.295979307000039, "count": 18191, "is_parallel": true, "self": 6.295979307000039 }, "communicator.exchange": { "total": 181.50708347098123, "count": 18191, "is_parallel": true, "self": 181.50708347098123 }, "steps_from_proto": { "total": 37.92307565701583, "count": 18191, "is_parallel": true, "self": 6.977938630070753, "children": { "_process_rank_one_or_two_observation": { "total": 30.945137026945076, "count": 181910, "is_parallel": true, "self": 30.945137026945076 } } } } } } } } } } }, "trainer_advance": { "total": 144.31709579200503, "count": 18192, "self": 0.5320394700145243, "children": { "process_trajectory": { "total": 33.061040467990324, "count": 18192, "self": 32.54431096299027, "children": { "RLTrainer._checkpoint": { "total": 0.5167295050000575, "count": 4, "self": 0.5167295050000575 } } }, "_update_policy": { "total": 110.72401585400019, "count": 90, "self": 47.392693440000926, "children": { "TorchPPOOptimizer.update": { "total": 63.33132241399926, "count": 4587, "self": 63.33132241399926 } } } } } } }, "trainer_threads": { "total": 1.1949998679483542e-06, "count": 1, "self": 1.1949998679483542e-06 }, "TrainerController._save_models": { "total": 0.09944668499997533, "count": 1, "self": 0.0013223160001416545, "children": { "RLTrainer._checkpoint": { "total": 0.09812436899983368, "count": 1, "self": 0.09812436899983368 } } } } } } }