{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404542088508606, "min": 1.404542088508606, "max": 1.4284346103668213, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69132.96875, "min": 69132.96875, "max": 75728.875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.87961165048544, "min": 89.6896551724138, "max": 389.765625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49378.0, "min": 48953.0, "max": 50069.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999959.0, "min": 49616.0, "max": 1999959.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999959.0, "min": 49616.0, "max": 1999959.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.426220417022705, "min": 0.1415736973285675, "max": 2.4954614639282227, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1249.5035400390625, "min": 17.979860305786133, "max": 1307.89990234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7215249994426096, "min": 1.7891718453075003, "max": 3.947358890111188, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1916.585374712944, "min": 227.22482435405254, "max": 2073.1430832743645, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7215249994426096, "min": 1.7891718453075003, "max": 3.947358890111188, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1916.585374712944, "min": 227.22482435405254, "max": 2073.1430832743645, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01877896684616442, "min": 0.013793709580366138, "max": 0.018836396675275563, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05633690053849326, "min": 0.02783947930341431, "max": 0.05633690053849326, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.058057321401105984, "min": 0.020410086152454217, "max": 0.058057321401105984, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17417196420331796, "min": 0.040820172304908434, "max": 0.17417196420331796, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.128098957333343e-06, "min": 3.128098957333343e-06, "max": 0.00029537625154124993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.38429687200003e-06, "min": 9.38429687200003e-06, "max": 0.0008443356185547999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10104266666666667, "min": 0.10104266666666667, "max": 0.19845875000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.303128, "min": 0.20722655000000004, "max": 0.5814452, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.202906666666683e-05, "min": 6.202906666666683e-05, "max": 0.004923091625000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018608720000000048, "min": 0.00018608720000000048, "max": 0.01407411548, "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": "1716923193", "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": "1716928097" }, "total": 4903.782488551999, "count": 1, "self": 0.5928459799988559, "children": { "run_training.setup": { "total": 0.07585510500007331, "count": 1, "self": 0.07585510500007331 }, "TrainerController.start_learning": { "total": 4903.113787467, "count": 1, "self": 9.035434174889815, "children": { "TrainerController._reset_env": { "total": 4.592686447999995, "count": 1, "self": 4.592686447999995 }, "TrainerController.advance": { "total": 4889.36676624311, "count": 231440, "self": 8.318507440091707, "children": { "env_step": { "total": 3127.4713308679816, "count": 231440, "self": 2612.6937281372757, "children": { "SubprocessEnvManager._take_step": { "total": 509.21873294390036, "count": 231440, "self": 33.933035536023, "children": { "TorchPolicy.evaluate": { "total": 475.28569740787736, "count": 222882, "self": 475.28569740787736 } } }, "workers": { "total": 5.558869786805417, "count": 231440, "self": 0.0, "children": { "worker_root": { "total": 4889.391045860905, "count": 231440, "is_parallel": true, "self": 2821.291434141734, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011959370000340641, "count": 1, "is_parallel": true, "self": 0.00032938900005774485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008665479999763193, "count": 2, "is_parallel": true, "self": 0.0008665479999763193 } } }, "UnityEnvironment.step": { "total": 0.037833417000001646, "count": 1, "is_parallel": true, "self": 0.0005203050000091025, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023038900008032215, "count": 1, "is_parallel": true, "self": 0.00023038900008032215 }, "communicator.exchange": { "total": 0.03607495599999311, "count": 1, "is_parallel": true, "self": 0.03607495599999311 }, "steps_from_proto": { "total": 0.001007766999919113, "count": 1, "is_parallel": true, "self": 0.0002620539997906235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007457130001284895, "count": 2, "is_parallel": true, "self": 0.0007457130001284895 } } } } } } }, "UnityEnvironment.step": { "total": 2068.099611719171, "count": 231439, "is_parallel": true, "self": 64.54428219771398, "children": { "UnityEnvironment._generate_step_input": { "total": 115.44028239294107, "count": 231439, "is_parallel": true, "self": 115.44028239294107 }, "communicator.exchange": { "total": 1746.2416262081106, "count": 231439, "is_parallel": true, "self": 1746.2416262081106 }, "steps_from_proto": { "total": 141.87342092040558, "count": 231439, "is_parallel": true, "self": 44.938069174396105, "children": { "_process_rank_one_or_two_observation": { "total": 96.93535174600947, "count": 462878, "is_parallel": true, "self": 96.93535174600947 } } } } } } } } } } }, "trainer_advance": { "total": 1753.5769279350366, "count": 231440, "self": 12.921770972184959, "children": { "process_trajectory": { "total": 261.61372475185476, "count": 231440, "self": 260.1336885458545, "children": { "RLTrainer._checkpoint": { "total": 1.4800362060002499, "count": 10, "self": 1.4800362060002499 } } }, "_update_policy": { "total": 1479.0414322109968, "count": 97, "self": 352.91656365601784, "children": { "TorchPPOOptimizer.update": { "total": 1126.124868554979, "count": 2910, "self": 1126.124868554979 } } } } } } }, "trainer_threads": { "total": 2.016000507865101e-06, "count": 1, "self": 2.016000507865101e-06 }, "TrainerController._save_models": { "total": 0.11889858500035189, "count": 1, "self": 0.002978363000693207, "children": { "RLTrainer._checkpoint": { "total": 0.11592022199965868, "count": 1, "self": 0.11592022199965868 } } } } } } }