{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4003328084945679, "min": 1.4003328084945679, "max": 1.4268192052841187, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69631.546875, "min": 67694.78125, "max": 76667.125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 102.36550308008214, "min": 94.45124282982792, "max": 389.1240310077519, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49852.0, "min": 48958.0, "max": 50197.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999614.0, "min": 49969.0, "max": 1999614.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999614.0, "min": 49969.0, "max": 1999614.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3830080032348633, "min": -0.008995944634079933, "max": 2.4216861724853516, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1160.52490234375, "min": -1.1514809131622314, "max": 1240.837890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7184661074830276, "min": 1.8396811578422785, "max": 3.8733034093908016, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1810.8929943442345, "min": 235.47918820381165, "max": 2002.3528826832771, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7184661074830276, "min": 1.8396811578422785, "max": 3.8733034093908016, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1810.8929943442345, "min": 235.47918820381165, "max": 2002.3528826832771, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017587505817128757, "min": 0.013792804331751542, "max": 0.019923504476901145, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05276251745138627, "min": 0.027585608663503083, "max": 0.05525532867419922, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.045406616106629376, "min": 0.02391973709066709, "max": 0.05815416698654493, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13621984831988812, "min": 0.04783947418133418, "max": 0.17083036378026006, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2207989264333428e-06, "min": 3.2207989264333428e-06, "max": 0.0002952963015678999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.662396779300029e-06, "min": 9.662396779300029e-06, "max": 0.0008438935687021498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107356666666667, "min": 0.10107356666666667, "max": 0.19843210000000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032207, "min": 0.20732194999999998, "max": 0.5812978500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.357097666666683e-05, "min": 6.357097666666683e-05, "max": 0.004921761789999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019071293000000048, "min": 0.00019071293000000048, "max": 0.014066762715, "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": "1749450803", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749453154" }, "total": 2351.192432979, "count": 1, "self": 0.4940550140004234, "children": { "run_training.setup": { "total": 0.023282630999915455, "count": 1, "self": 0.023282630999915455 }, "TrainerController.start_learning": { "total": 2350.6750953339997, "count": 1, "self": 4.181193876874659, "children": { "TrainerController._reset_env": { "total": 3.569802956999979, "count": 1, "self": 3.569802956999979 }, "TrainerController.advance": { "total": 2342.8149832311246, "count": 231909, "self": 4.315756347099523, "children": { "env_step": { "total": 1864.1330183980047, "count": 231909, "self": 1454.3766322509896, "children": { "SubprocessEnvManager._take_step": { "total": 407.26470918901725, "count": 231909, "self": 15.31220902307814, "children": { "TorchPolicy.evaluate": { "total": 391.9525001659391, "count": 222986, "self": 391.9525001659391 } } }, "workers": { "total": 2.4916769579979245, "count": 231909, "self": 0.0, "children": { "worker_root": { "total": 2343.8518492770922, "count": 231909, "is_parallel": true, "self": 1156.4777134821807, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000871459999984836, "count": 1, "is_parallel": true, "self": 0.00024221499995746854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006292450000273675, "count": 2, "is_parallel": true, "self": 0.0006292450000273675 } } }, "UnityEnvironment.step": { "total": 0.045082664000005934, "count": 1, "is_parallel": true, "self": 0.0002620829999386842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001771429999735119, "count": 1, "is_parallel": true, "self": 0.0001771429999735119 }, "communicator.exchange": { "total": 0.043793181000069126, "count": 1, "is_parallel": true, "self": 0.043793181000069126 }, "steps_from_proto": { "total": 0.0008502570000246124, "count": 1, "is_parallel": true, "self": 0.00018045700005586696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006697999999687454, "count": 2, "is_parallel": true, "self": 0.0006697999999687454 } } } } } } }, "UnityEnvironment.step": { "total": 1187.3741357949116, "count": 231908, "is_parallel": true, "self": 35.76861655504581, "children": { "UnityEnvironment._generate_step_input": { "total": 78.47995957500666, "count": 231908, "is_parallel": true, "self": 78.47995957500666 }, "communicator.exchange": { "total": 989.8933652948839, "count": 231908, "is_parallel": true, "self": 989.8933652948839 }, "steps_from_proto": { "total": 83.23219436997522, "count": 231908, "is_parallel": true, "self": 28.96314932000473, "children": { "_process_rank_one_or_two_observation": { "total": 54.26904504997049, "count": 463816, "is_parallel": true, "self": 54.26904504997049 } } } } } } } } } } }, "trainer_advance": { "total": 474.36620848602047, "count": 231909, "self": 5.9728400941078235, "children": { "process_trajectory": { "total": 153.1502077049115, "count": 231909, "self": 151.86212860091155, "children": { "RLTrainer._checkpoint": { "total": 1.2880791039999622, "count": 10, "self": 1.2880791039999622 } } }, "_update_policy": { "total": 315.24316068700114, "count": 97, "self": 250.25219089799998, "children": { "TorchPPOOptimizer.update": { "total": 64.99096978900116, "count": 2910, "self": 64.99096978900116 } } } } } } }, "trainer_threads": { "total": 1.0440003279654775e-06, "count": 1, "self": 1.0440003279654775e-06 }, "TrainerController._save_models": { "total": 0.10911422500021217, "count": 1, "self": 0.0018944350003948784, "children": { "RLTrainer._checkpoint": { "total": 0.1072197899998173, "count": 1, "self": 0.1072197899998173 } } } } } } }