{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403841257095337, "min": 1.4038336277008057, "max": 1.4299356937408447, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71280.0390625, "min": 68695.5703125, "max": 76897.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.1264367816092, "min": 83.45101351351352, "max": 408.9430894308943, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49656.0, "min": 48840.0, "max": 50300.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999519.0, "min": 49756.0, "max": 1999519.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999519.0, "min": 49756.0, "max": 1999519.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.375016212463379, "min": 0.06490364670753479, "max": 2.432133436203003, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1239.7584228515625, "min": 7.9182448387146, "max": 1415.4788818359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7104600122148508, "min": 1.939149587369356, "max": 3.933459283855125, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1936.860126376152, "min": 236.57624965906143, "max": 2237.3878024220467, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7104600122148508, "min": 1.939149587369356, "max": 3.933459283855125, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1936.860126376152, "min": 236.57624965906143, "max": 2237.3878024220467, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016222141753274227, "min": 0.014065655128797518, "max": 0.02063414677169122, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048666425259822677, "min": 0.028131310257595035, "max": 0.061902440315073665, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051034690377612914, "min": 0.023581497867902118, "max": 0.05908637270331383, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15310407113283875, "min": 0.047162995735804236, "max": 0.17461602129042147, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6827987724333284e-06, "min": 3.6827987724333284e-06, "max": 0.0002953775265408249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1048396317299985e-05, "min": 1.1048396317299985e-05, "max": 0.00084426826857725, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012275666666667, "min": 0.1012275666666667, "max": 0.198459175, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036827000000001, "min": 0.20762975000000003, "max": 0.58142275, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.125557666666659e-05, "min": 7.125557666666659e-05, "max": 0.004923112832499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021376672999999977, "min": 0.00021376672999999977, "max": 0.014072995225000001, "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": "1719740678", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719745200" }, "total": 4521.906587909, "count": 1, "self": 0.6425635560008232, "children": { "run_training.setup": { "total": 0.07715158899998187, "count": 1, "self": 0.07715158899998187 }, "TrainerController.start_learning": { "total": 4521.186872763999, "count": 1, "self": 8.167284088181077, "children": { "TrainerController._reset_env": { "total": 4.457575820999978, "count": 1, "self": 4.457575820999978 }, "TrainerController.advance": { "total": 4508.445580077817, "count": 231802, "self": 7.960788329653951, "children": { "env_step": { "total": 2924.995103173195, "count": 231802, "self": 2457.4100941511497, "children": { "SubprocessEnvManager._take_step": { "total": 462.20995998308445, "count": 231802, "self": 30.692127030102142, "children": { "TorchPolicy.evaluate": { "total": 431.5178329529823, "count": 222993, "self": 431.5178329529823 } } }, "workers": { "total": 5.375049038960924, "count": 231802, "self": 0.0, "children": { "worker_root": { "total": 4507.306419080121, "count": 231802, "is_parallel": true, "self": 2569.5904892321096, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012693959999978688, "count": 1, "is_parallel": true, "self": 0.0003180190000193761, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009513769999784927, "count": 2, "is_parallel": true, "self": 0.0009513769999784927 } } }, "UnityEnvironment.step": { "total": 0.04453695400002289, "count": 1, "is_parallel": true, "self": 0.0005257900000970039, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003575859999500608, "count": 1, "is_parallel": true, "self": 0.0003575859999500608 }, "communicator.exchange": { "total": 0.0426017290000118, "count": 1, "is_parallel": true, "self": 0.0426017290000118 }, "steps_from_proto": { "total": 0.0010518489999640224, "count": 1, "is_parallel": true, "self": 0.00027172999989488744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007801190000691349, "count": 2, "is_parallel": true, "self": 0.0007801190000691349 } } } } } } }, "UnityEnvironment.step": { "total": 1937.715929848011, "count": 231801, "is_parallel": true, "self": 62.96867078533114, "children": { "UnityEnvironment._generate_step_input": { "total": 111.87381431181609, "count": 231801, "is_parallel": true, "self": 111.87381431181609 }, "communicator.exchange": { "total": 1625.153083068884, "count": 231801, "is_parallel": true, "self": 1625.153083068884 }, "steps_from_proto": { "total": 137.72036168197985, "count": 231801, "is_parallel": true, "self": 44.38225073199624, "children": { "_process_rank_one_or_two_observation": { "total": 93.33811094998362, "count": 463602, "is_parallel": true, "self": 93.33811094998362 } } } } } } } } } } }, "trainer_advance": { "total": 1575.4896885749683, "count": 231802, "self": 12.505439049846473, "children": { "process_trajectory": { "total": 246.6388989651232, "count": 231802, "self": 245.23366671012423, "children": { "RLTrainer._checkpoint": { "total": 1.405232254998964, "count": 10, "self": 1.405232254998964 } } }, "_update_policy": { "total": 1316.3453505599987, "count": 97, "self": 339.7417975080076, "children": { "TorchPPOOptimizer.update": { "total": 976.6035530519911, "count": 2910, "self": 976.6035530519911 } } } } } } }, "trainer_threads": { "total": 1.2440004866220988e-06, "count": 1, "self": 1.2440004866220988e-06 }, "TrainerController._save_models": { "total": 0.11643153300065023, "count": 1, "self": 0.003100875001109671, "children": { "RLTrainer._checkpoint": { "total": 0.11333065799954056, "count": 1, "self": 0.11333065799954056 } } } } } } }