{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3998901844024658, "min": 1.3998901844024658, "max": 1.4287067651748657, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69713.1328125, "min": 68445.1875, "max": 78140.3515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.28313253012048, "min": 68.52433936022253, "max": 381.55725190839695, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49324.0, "min": 49258.0, "max": 49984.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999846.0, "min": 49978.0, "max": 1999846.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999846.0, "min": 49978.0, "max": 1999846.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5153849124908447, "min": 0.12736664712429047, "max": 2.5335588455200195, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1670.215576171875, "min": 16.55766487121582, "max": 1764.59716796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 4.01243085396218, "min": 1.734875643482575, "max": 4.091868463785025, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2664.2540870308876, "min": 225.53383365273476, "max": 2762.1322083473206, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 4.01243085396218, "min": 1.734875643482575, "max": 4.091868463785025, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2664.2540870308876, "min": 225.53383365273476, "max": 2762.1322083473206, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01599631953043475, "min": 0.013417540630972427, "max": 0.02014944220023204, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047988958591304254, "min": 0.029630805421038534, "max": 0.060448326600696115, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056284126184052895, "min": 0.02113232286646962, "max": 0.0619375686471661, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16885237855215868, "min": 0.04226464573293924, "max": 0.17654209608832994, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.020998659699994e-06, "min": 4.020998659699994e-06, "max": 0.00029528287657237497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.2062995979099982e-05, "min": 1.2062995979099982e-05, "max": 0.00084401206866265, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1013403, "min": 0.1013403, "max": 0.198427625, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3040209, "min": 0.20780985, "max": 0.5813373500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.68809699999999e-05, "min": 7.68809699999999e-05, "max": 0.0049215384875, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002306429099999997, "min": 0.0002306429099999997, "max": 0.014068733764999997, "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": "1676559995", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676562377" }, "total": 2381.785822795, "count": 1, "self": 0.4387311350001255, "children": { "run_training.setup": { "total": 0.11778803899983359, "count": 1, "self": 0.11778803899983359 }, "TrainerController.start_learning": { "total": 2381.2293036210003, "count": 1, "self": 4.123217922978256, "children": { "TrainerController._reset_env": { "total": 10.123141165000106, "count": 1, "self": 10.123141165000106 }, "TrainerController.advance": { "total": 2366.863461569022, "count": 233526, "self": 4.484354636882017, "children": { "env_step": { "total": 1845.1681779400772, "count": 233526, "self": 1544.2883803120683, "children": { "SubprocessEnvManager._take_step": { "total": 298.1341406220208, "count": 233526, "self": 15.303997972955813, "children": { "TorchPolicy.evaluate": { "total": 282.830142649065, "count": 222902, "self": 70.83652970313119, "children": { "TorchPolicy.sample_actions": { "total": 211.99361294593382, "count": 222902, "self": 211.99361294593382 } } } } }, "workers": { "total": 2.7456570059880505, "count": 233526, "self": 0.0, "children": { "worker_root": { "total": 2373.4046847380373, "count": 233526, "is_parallel": true, "self": 1114.4509416089302, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022199649999947724, "count": 1, "is_parallel": true, "self": 0.000345831000004182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018741339999905904, "count": 2, "is_parallel": true, "self": 0.0018741339999905904 } } }, "UnityEnvironment.step": { "total": 0.04455828300001485, "count": 1, "is_parallel": true, "self": 0.0002981760003422096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019339299979037605, "count": 1, "is_parallel": true, "self": 0.00019339299979037605 }, "communicator.exchange": { "total": 0.043339724999896134, "count": 1, "is_parallel": true, "self": 0.043339724999896134 }, "steps_from_proto": { "total": 0.0007269889999861334, "count": 1, "is_parallel": true, "self": 0.0002551630000198202, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047182599996631325, "count": 2, "is_parallel": true, "self": 0.00047182599996631325 } } } } } } }, "UnityEnvironment.step": { "total": 1258.9537431291071, "count": 233525, "is_parallel": true, "self": 38.0015809380302, "children": { "UnityEnvironment._generate_step_input": { "total": 76.85388828902273, "count": 233525, "is_parallel": true, "self": 76.85388828902273 }, "communicator.exchange": { "total": 1038.8551135641094, "count": 233525, "is_parallel": true, "self": 1038.8551135641094 }, "steps_from_proto": { "total": 105.2431603379448, "count": 233525, "is_parallel": true, "self": 37.847484832783266, "children": { "_process_rank_one_or_two_observation": { "total": 67.39567550516153, "count": 467050, "is_parallel": true, "self": 67.39567550516153 } } } } } } } } } } }, "trainer_advance": { "total": 517.2109289920629, "count": 233526, "self": 6.361679629132823, "children": { "process_trajectory": { "total": 165.9670474549314, "count": 233526, "self": 164.779882973932, "children": { "RLTrainer._checkpoint": { "total": 1.1871644809993995, "count": 10, "self": 1.1871644809993995 } } }, "_update_policy": { "total": 344.8822019079987, "count": 97, "self": 288.7258334509886, "children": { "TorchPPOOptimizer.update": { "total": 56.1563684570101, "count": 2910, "self": 56.1563684570101 } } } } } } }, "trainer_threads": { "total": 7.959997674333863e-07, "count": 1, "self": 7.959997674333863e-07 }, "TrainerController._save_models": { "total": 0.11948216800010414, "count": 1, "self": 0.0020683220000137226, "children": { "RLTrainer._checkpoint": { "total": 0.11741384600009042, "count": 1, "self": 0.11741384600009042 } } } } } } }