{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405076503753662, "min": 1.405076503753662, "max": 1.4282598495483398, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69360.1953125, "min": 69234.9140625, "max": 77606.1796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.7936210131332, "min": 80.84843492586491, "max": 398.26771653543307, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49459.0, "min": 48795.0, "max": 50580.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999976.0, "min": 49797.0, "max": 1999976.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999976.0, "min": 49797.0, "max": 1999976.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4578118324279785, "min": 0.13486307859420776, "max": 2.4985909461975098, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1310.013671875, "min": 16.857885360717773, "max": 1490.486572265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7843444745491412, "min": 1.838410358428955, "max": 3.94498549412798, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2017.0556049346924, "min": 229.80129480361938, "max": 2307.6465750336647, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7843444745491412, "min": 1.838410358428955, "max": 3.94498549412798, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2017.0556049346924, "min": 229.80129480361938, "max": 2307.6465750336647, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017311833216161986, "min": 0.012337864890772227, "max": 0.018811922698902587, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051935499648485955, "min": 0.024675729781544455, "max": 0.056274867443911115, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.048591214294234915, "min": 0.022289028204977513, "max": 0.05911690214027961, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14577364288270475, "min": 0.044578056409955026, "max": 0.17392526442805928, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5021988326333305e-06, "min": 3.5021988326333305e-06, "max": 0.00029536845154385, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0506596497899991e-05, "min": 1.0506596497899991e-05, "max": 0.00084429166856945, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116736666666666, "min": 0.10116736666666666, "max": 0.19845614999999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035021, "min": 0.20755279999999998, "max": 0.5814305500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.825159666666662e-05, "min": 6.825159666666662e-05, "max": 0.004922961884999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020475478999999985, "min": 0.00020475478999999985, "max": 0.014073384445, "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": "1740707472", "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=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740709991" }, "total": 2518.482109939, "count": 1, "self": 0.43974303399954806, "children": { "run_training.setup": { "total": 0.022626840000157245, "count": 1, "self": 0.022626840000157245 }, "TrainerController.start_learning": { "total": 2518.0197400650004, "count": 1, "self": 4.576362336844795, "children": { "TrainerController._reset_env": { "total": 3.075277982999978, "count": 1, "self": 3.075277982999978 }, "TrainerController.advance": { "total": 2510.2470596871553, "count": 232362, "self": 4.847788437797135, "children": { "env_step": { "total": 2033.1902643132953, "count": 232362, "self": 1589.5655711148838, "children": { "SubprocessEnvManager._take_step": { "total": 440.8487260902066, "count": 232362, "self": 15.997514591999789, "children": { "TorchPolicy.evaluate": { "total": 424.8512114982068, "count": 222940, "self": 424.8512114982068 } } }, "workers": { "total": 2.7759671082048953, "count": 232362, "self": 0.0, "children": { "worker_root": { "total": 2510.5769286520517, "count": 232362, "is_parallel": true, "self": 1217.1174638850916, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009368979999635485, "count": 1, "is_parallel": true, "self": 0.00025915700007317355, "children": { "_process_rank_one_or_two_observation": { "total": 0.000677740999890375, "count": 2, "is_parallel": true, "self": 0.000677740999890375 } } }, "UnityEnvironment.step": { "total": 0.030254819999754545, "count": 1, "is_parallel": true, "self": 0.00026207699920632876, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020200600010866765, "count": 1, "is_parallel": true, "self": 0.00020200600010866765 }, "communicator.exchange": { "total": 0.02892629300004046, "count": 1, "is_parallel": true, "self": 0.02892629300004046 }, "steps_from_proto": { "total": 0.0008644440003990894, "count": 1, "is_parallel": true, "self": 0.0001903590009533218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006740849994457676, "count": 2, "is_parallel": true, "self": 0.0006740849994457676 } } } } } } }, "UnityEnvironment.step": { "total": 1293.45946476696, "count": 232361, "is_parallel": true, "self": 36.807282986665086, "children": { "UnityEnvironment._generate_step_input": { "total": 84.90802561602777, "count": 232361, "is_parallel": true, "self": 84.90802561602777 }, "communicator.exchange": { "total": 1082.3082343173064, "count": 232361, "is_parallel": true, "self": 1082.3082343173064 }, "steps_from_proto": { "total": 89.43592184696081, "count": 232361, "is_parallel": true, "self": 33.2821208415171, "children": { "_process_rank_one_or_two_observation": { "total": 56.15380100544371, "count": 464722, "is_parallel": true, "self": 56.15380100544371 } } } } } } } } } } }, "trainer_advance": { "total": 472.2090069360629, "count": 232362, "self": 6.883326185225087, "children": { "process_trajectory": { "total": 171.7139849748437, "count": 232362, "self": 170.32284648084442, "children": { "RLTrainer._checkpoint": { "total": 1.3911384939992786, "count": 10, "self": 1.3911384939992786 } } }, "_update_policy": { "total": 293.6116957759941, "count": 97, "self": 230.53636431199448, "children": { "TorchPPOOptimizer.update": { "total": 63.075331463999646, "count": 2910, "self": 63.075331463999646 } } } } } } }, "trainer_threads": { "total": 9.839995982474647e-07, "count": 1, "self": 9.839995982474647e-07 }, "TrainerController._save_models": { "total": 0.12103907400069147, "count": 1, "self": 0.001963215000614582, "children": { "RLTrainer._checkpoint": { "total": 0.11907585900007689, "count": 1, "self": 0.11907585900007689 } } } } } } }