{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4048881530761719, "min": 1.4048881530761719, "max": 1.4287546873092651, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70779.671875, "min": 68921.09375, "max": 78237.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 72.74778761061947, "min": 71.65095729013255, "max": 399.072, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49323.0, "min": 48651.0, "max": 50141.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999973.0, "min": 49916.0, "max": 1999973.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999973.0, "min": 49916.0, "max": 1999973.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4536004066467285, "min": 0.13399046659469604, "max": 2.497018814086914, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1663.541015625, "min": 16.614818572998047, "max": 1663.541015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8301785953101155, "min": 1.8372729483150667, "max": 3.9667634256914552, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2596.8610876202583, "min": 227.82184559106827, "max": 2614.3891227841377, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8301785953101155, "min": 1.8372729483150667, "max": 3.9667634256914552, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2596.8610876202583, "min": 227.82184559106827, "max": 2614.3891227841377, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018571364098978745, "min": 0.013794821179180872, "max": 0.020753360802902736, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05571409229693624, "min": 0.027589642358361744, "max": 0.06226008240870821, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.061015796495808496, "min": 0.023085488192737102, "max": 0.06411688476800918, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1830473894874255, "min": 0.046170976385474204, "max": 0.1830473894874255, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7334987555333315e-06, "min": 3.7334987555333315e-06, "max": 0.0002953689015437, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1200496266599994e-05, "min": 1.1200496266599994e-05, "max": 0.0008440947186350999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124446666666669, "min": 0.10124446666666669, "max": 0.19845629999999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30373340000000004, "min": 0.20767619999999998, "max": 0.5813649000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.209888666666663e-05, "min": 7.209888666666663e-05, "max": 0.00492296937, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002162966599999999, "min": 0.0002162966599999999, "max": 0.014070108509999998, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1766824792", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1766827494" }, "total": 2701.6810872039996, "count": 1, "self": 0.49968928499993126, "children": { "run_training.setup": { "total": 0.029045533000044088, "count": 1, "self": 0.029045533000044088 }, "TrainerController.start_learning": { "total": 2701.1523523859996, "count": 1, "self": 4.875228993080782, "children": { "TrainerController._reset_env": { "total": 2.9778719260000344, "count": 1, "self": 2.9778719260000344 }, "TrainerController.advance": { "total": 2693.199281381919, "count": 233295, "self": 4.707050352130864, "children": { "env_step": { "total": 2203.924486341823, "count": 233295, "self": 1774.7685206409367, "children": { "SubprocessEnvManager._take_step": { "total": 426.1455956779961, "count": 233295, "self": 16.727292574006583, "children": { "TorchPolicy.evaluate": { "total": 409.4183031039895, "count": 222976, "self": 409.4183031039895 } } }, "workers": { "total": 3.0103700228902426, "count": 233295, "self": 0.0, "children": { "worker_root": { "total": 2687.868629373014, "count": 233295, "is_parallel": true, "self": 1252.892162846016, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009055350000153339, "count": 1, "is_parallel": true, "self": 0.0002777229999537667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006278120000615672, "count": 2, "is_parallel": true, "self": 0.0006278120000615672 } } }, "UnityEnvironment.step": { "total": 0.03139284199994563, "count": 1, "is_parallel": true, "self": 0.0003406700000141427, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020160799999757728, "count": 1, "is_parallel": true, "self": 0.00020160799999757728 }, "communicator.exchange": { "total": 0.030076886999950148, "count": 1, "is_parallel": true, "self": 0.030076886999950148 }, "steps_from_proto": { "total": 0.0007736769999837634, "count": 1, "is_parallel": true, "self": 0.0002002429999947708, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005734339999889926, "count": 2, "is_parallel": true, "self": 0.0005734339999889926 } } } } } } }, "UnityEnvironment.step": { "total": 1434.976466526998, "count": 233294, "is_parallel": true, "self": 40.200035336090195, "children": { "UnityEnvironment._generate_step_input": { "total": 85.42477998900802, "count": 233294, "is_parallel": true, "self": 85.42477998900802 }, "communicator.exchange": { "total": 1213.3682827120037, "count": 233294, "is_parallel": true, "self": 1213.3682827120037 }, "steps_from_proto": { "total": 95.98336848989584, "count": 233294, "is_parallel": true, "self": 34.26579671172442, "children": { "_process_rank_one_or_two_observation": { "total": 61.71757177817142, "count": 466588, "is_parallel": true, "self": 61.71757177817142 } } } } } } } } } } }, "trainer_advance": { "total": 484.5677446879647, "count": 233295, "self": 7.3163010058081, "children": { "process_trajectory": { "total": 164.8264000251569, "count": 233295, "self": 163.64491495315758, "children": { "RLTrainer._checkpoint": { "total": 1.1814850719993046, "count": 10, "self": 1.1814850719993046 } } }, "_update_policy": { "total": 312.4250436569997, "count": 97, "self": 248.7002008970029, "children": { "TorchPPOOptimizer.update": { "total": 63.72484275999682, "count": 2910, "self": 63.72484275999682 } } } } } } }, "trainer_threads": { "total": 1.0229996405541897e-06, "count": 1, "self": 1.0229996405541897e-06 }, "TrainerController._save_models": { "total": 0.09996906200012745, "count": 1, "self": 0.001458508000268921, "children": { "RLTrainer._checkpoint": { "total": 0.09851055399985853, "count": 1, "self": 0.09851055399985853 } } } } } } }