{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4025437831878662, "min": 1.4025437831878662, "max": 1.4279643297195435, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68517.0703125, "min": 68517.0703125, "max": 77128.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.41713221601489, "min": 86.59194395796848, "max": 394.59375, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49628.0, "min": 48960.0, "max": 50508.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999433.0, "min": 49900.0, "max": 1999433.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999433.0, "min": 49900.0, "max": 1999433.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.436884880065918, "min": 0.13354480266571045, "max": 2.464599132537842, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1308.607177734375, "min": 16.960189819335938, "max": 1394.35986328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.811208130927059, "min": 1.6266648959456467, "max": 3.9096504801418632, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2046.6187663078308, "min": 206.58644178509712, "max": 2149.31708753109, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.811208130927059, "min": 1.6266648959456467, "max": 3.9096504801418632, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2046.6187663078308, "min": 206.58644178509712, "max": 2149.31708753109, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017878844584791092, "min": 0.0117617288895417, "max": 0.019849774881731716, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05363653375437328, "min": 0.0235234577790834, "max": 0.05739227697292032, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06360755711793899, "min": 0.02137187048792839, "max": 0.06483517655481895, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19082267135381697, "min": 0.04274374097585678, "max": 0.19082267135381697, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3223988925666785e-06, "min": 3.3223988925666785e-06, "max": 0.00029536072654642496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.967196677700035e-06, "min": 9.967196677700035e-06, "max": 0.0008442567185810999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110743333333332, "min": 0.10110743333333332, "max": 0.19845357500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30332229999999993, "min": 0.2073893, "max": 0.5814189000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.52609233333335e-05, "min": 6.52609233333335e-05, "max": 0.004922833392500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001957827700000005, "min": 0.0001957827700000005, "max": 0.01407280311, "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": "1709280996", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709283259" }, "total": 2263.797690595, "count": 1, "self": 0.435051772999941, "children": { "run_training.setup": { "total": 0.050640224999938255, "count": 1, "self": 0.050640224999938255 }, "TrainerController.start_learning": { "total": 2263.311998597, "count": 1, "self": 4.1556047689769, "children": { "TrainerController._reset_env": { "total": 3.6918698489999997, "count": 1, "self": 3.6918698489999997 }, "TrainerController.advance": { "total": 2255.3519276950237, "count": 231691, "self": 4.248104470814724, "children": { "env_step": { "total": 1789.0012527012184, "count": 231691, "self": 1479.8999652182756, "children": { "SubprocessEnvManager._take_step": { "total": 306.45421031197543, "count": 231691, "self": 16.620804368940185, "children": { "TorchPolicy.evaluate": { "total": 289.83340594303525, "count": 222898, "self": 289.83340594303525 } } }, "workers": { "total": 2.6470771709672363, "count": 231691, "self": 0.0, "children": { "worker_root": { "total": 2256.2002797509535, "count": 231691, "is_parallel": true, "self": 1050.861300006854, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001052823999998509, "count": 1, "is_parallel": true, "self": 0.0002894299999525174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007633940000459916, "count": 2, "is_parallel": true, "self": 0.0007633940000459916 } } }, "UnityEnvironment.step": { "total": 0.030060033000040676, "count": 1, "is_parallel": true, "self": 0.00034252099999321217, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020124000002397224, "count": 1, "is_parallel": true, "self": 0.00020124000002397224 }, "communicator.exchange": { "total": 0.0288138240000535, "count": 1, "is_parallel": true, "self": 0.0288138240000535 }, "steps_from_proto": { "total": 0.0007024479999699906, "count": 1, "is_parallel": true, "self": 0.00018306700007997279, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005193809998900178, "count": 2, "is_parallel": true, "self": 0.0005193809998900178 } } } } } } }, "UnityEnvironment.step": { "total": 1205.3389797440996, "count": 231690, "is_parallel": true, "self": 39.72869423496422, "children": { "UnityEnvironment._generate_step_input": { "total": 80.1445173590514, "count": 231690, "is_parallel": true, "self": 80.1445173590514 }, "communicator.exchange": { "total": 997.2786828290836, "count": 231690, "is_parallel": true, "self": 997.2786828290836 }, "steps_from_proto": { "total": 88.18708532100027, "count": 231690, "is_parallel": true, "self": 30.617927323100048, "children": { "_process_rank_one_or_two_observation": { "total": 57.56915799790022, "count": 463380, "is_parallel": true, "self": 57.56915799790022 } } } } } } } } } } }, "trainer_advance": { "total": 462.10257052299085, "count": 231691, "self": 6.002583906987184, "children": { "process_trajectory": { "total": 142.1060129500048, "count": 231691, "self": 140.88804760100413, "children": { "RLTrainer._checkpoint": { "total": 1.2179653490006785, "count": 10, "self": 1.2179653490006785 } } }, "_update_policy": { "total": 313.99397366599885, "count": 97, "self": 251.79469449000226, "children": { "TorchPPOOptimizer.update": { "total": 62.199279175996594, "count": 2910, "self": 62.199279175996594 } } } } } } }, "trainer_threads": { "total": 9.129998943535611e-07, "count": 1, "self": 9.129998943535611e-07 }, "TrainerController._save_models": { "total": 0.11259537099977024, "count": 1, "self": 0.0019708559998434794, "children": { "RLTrainer._checkpoint": { "total": 0.11062451499992676, "count": 1, "self": 0.11062451499992676 } } } } } } }