{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.2851881980895996, "min": 2.2851881980895996, "max": 2.863436222076416, "count": 5 }, "SnowballTarget.Policy.Entropy.sum": { "value": 23327.201171875, "min": 23327.201171875, "max": 29229.95703125, "count": 5 }, "SnowballTarget.Step.mean": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Step.sum": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.90823221206665, "min": 0.5719503164291382, "max": 4.90823221206665, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 952.197021484375, "min": 110.95835876464844, "max": 952.197021484375, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0659994036478057, "min": 0.06516088840336351, "max": 0.0723172462998442, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2639976145912228, "min": 0.2639976145912228, "max": 0.36158623149922103, "count": 5 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2905423788755548, "min": 0.141575666758524, "max": 0.2905423788755548, "count": 5 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1621695155022191, "min": 0.566302667034096, "max": 1.3247911702184116, "count": 5 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.9928090024000003e-05, "min": 2.9928090024000003e-05, "max": 0.00026752801082399996, "count": 5 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00011971236009600001, "min": 0.00011971236009600001, "max": 0.0010701120432959998, "count": 5 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10997600000000002, "min": 0.10997600000000002, "max": 0.18917599999999998, "count": 5 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4399040000000001, "min": 0.4399040000000001, "max": 0.8468800000000001, "count": 5 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0005078024, "min": 0.0005078024, "max": 0.0044598824, "count": 5 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0020312096, "min": 0.0020312096, "max": 0.0178395296, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 11.886363636363637, "min": 3.8636363636363638, "max": 11.886363636363637, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 523.0, "min": 170.0, "max": 606.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 11.886363636363637, "min": 3.8636363636363638, "max": 11.886363636363637, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 523.0, "min": 170.0, "max": 606.0, "count": 5 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1729485283", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729485393" }, "total": 109.49620752099997, "count": 1, "self": 0.4245238790000485, "children": { "run_training.setup": { "total": 0.052073823999990054, "count": 1, "self": 0.052073823999990054 }, "TrainerController.start_learning": { "total": 109.01960981799994, "count": 1, "self": 0.08957225399956315, "children": { "TrainerController._reset_env": { "total": 1.6209761740000204, "count": 1, "self": 1.6209761740000204 }, "TrainerController.advance": { "total": 107.21576100400034, "count": 4592, "self": 0.09169077099613787, "children": { "env_step": { "total": 75.06641918300375, "count": 4592, "self": 56.36825290100296, "children": { "SubprocessEnvManager._take_step": { "total": 18.64736323700083, "count": 4592, "self": 0.31530930900089515, "children": { "TorchPolicy.evaluate": { "total": 18.332053927999937, "count": 4592, "self": 18.332053927999937 } } }, "workers": { "total": 0.05080304499995236, "count": 4592, "self": 0.0, "children": { "worker_root": { "total": 108.49475175799853, "count": 4592, "is_parallel": true, "self": 59.136524051000265, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021947339999996984, "count": 1, "is_parallel": true, "self": 0.0006614869998884387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015332470001112597, "count": 10, "is_parallel": true, "self": 0.0015332470001112597 } } }, "UnityEnvironment.step": { "total": 0.034506729999975505, "count": 1, "is_parallel": true, "self": 0.0006338469997899665, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038313300001391326, "count": 1, "is_parallel": true, "self": 0.00038313300001391326 }, "communicator.exchange": { "total": 0.03169043600007626, "count": 1, "is_parallel": true, "self": 0.03169043600007626 }, "steps_from_proto": { "total": 0.0017993140000953645, "count": 1, "is_parallel": true, "self": 0.0003441309999061559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014551830001892085, "count": 10, "is_parallel": true, "self": 0.0014551830001892085 } } } } } } }, "UnityEnvironment.step": { "total": 49.358227706998264, "count": 4591, "is_parallel": true, "self": 2.526485178005146, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3401401509939888, "count": 4591, "is_parallel": true, "self": 1.3401401509939888 }, "communicator.exchange": { "total": 37.652184655997644, "count": 4591, "is_parallel": true, "self": 37.652184655997644 }, "steps_from_proto": { "total": 7.839417722001485, "count": 4591, "is_parallel": true, "self": 1.4192604110000957, "children": { "_process_rank_one_or_two_observation": { "total": 6.42015731100139, "count": 45910, "is_parallel": true, "self": 6.42015731100139 } } } } } } } } } } }, "trainer_advance": { "total": 32.05765105000046, "count": 4592, "self": 0.10775439800192999, "children": { "process_trajectory": { "total": 6.665141545998722, "count": 4592, "self": 6.5432424249986525, "children": { "RLTrainer._checkpoint": { "total": 0.1218991210000695, "count": 1, "self": 0.1218991210000695 } } }, "_update_policy": { "total": 25.284755105999807, "count": 22, "self": 10.298084988002984, "children": { "TorchPPOOptimizer.update": { "total": 14.986670117996823, "count": 1119, "self": 14.986670117996823 } } } } } } }, "trainer_threads": { "total": 1.0239999710393022e-06, "count": 1, "self": 1.0239999710393022e-06 }, "TrainerController._save_models": { "total": 0.09329936200003885, "count": 1, "self": 0.0011963020000393954, "children": { "RLTrainer._checkpoint": { "total": 0.09210305999999946, "count": 1, "self": 0.09210305999999946 } } } } } } }