{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4093549251556396, "min": 1.4093549251556396, "max": 1.4311820268630981, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71001.890625, "min": 68924.375, "max": 77073.5703125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.89003436426117, "min": 75.4480122324159, "max": 405.9349593495935, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49406.0, "min": 49122.0, "max": 50044.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49751.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49751.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5088016986846924, "min": 0.1855114847421646, "max": 2.5088016986846924, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1460.12255859375, "min": 22.632400512695312, "max": 1566.5498046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 4.025553583586748, "min": 1.7980861204569456, "max": 4.025553583586748, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2342.8721856474876, "min": 219.36650669574738, "max": 2477.9222781658173, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 4.025553583586748, "min": 1.7980861204569456, "max": 4.025553583586748, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2342.8721856474876, "min": 219.36650669574738, "max": 2477.9222781658173, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01808603250214623, "min": 0.013759414522064617, "max": 0.019638563502424707, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05425809750643869, "min": 0.027518829044129233, "max": 0.055976064533751924, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053173174709081644, "min": 0.02070392689978083, "max": 0.06267826234300931, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15951952412724493, "min": 0.04140785379956166, "max": 0.18244128574927648, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.417798860766668e-06, "min": 3.417798860766668e-06, "max": 0.00029529705156765003, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0253396582300004e-05, "min": 1.0253396582300004e-05, "max": 0.0008438544187152, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113923333333331, "min": 0.10113923333333331, "max": 0.19843235, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30341769999999996, "min": 0.20740575, "max": 0.5812847999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.684774333333337e-05, "min": 6.684774333333337e-05, "max": 0.004921774265, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002005432300000001, "min": 0.0002005432300000001, "max": 0.01406611152, "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": "1725304284", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725306747" }, "total": 2462.6028390700003, "count": 1, "self": 0.42971759000010934, "children": { "run_training.setup": { "total": 0.0537081009999838, "count": 1, "self": 0.0537081009999838 }, "TrainerController.start_learning": { "total": 2462.119413379, "count": 1, "self": 4.411234437955045, "children": { "TrainerController._reset_env": { "total": 2.0268248519998906, "count": 1, "self": 2.0268248519998906 }, "TrainerController.advance": { "total": 2455.564410181045, "count": 232809, "self": 4.608641600069859, "children": { "env_step": { "total": 1949.4697870649786, "count": 232809, "self": 1540.5479626729873, "children": { "SubprocessEnvManager._take_step": { "total": 406.1279170869957, "count": 232809, "self": 15.695649504873472, "children": { "TorchPolicy.evaluate": { "total": 390.4322675821222, "count": 222982, "self": 390.4322675821222 } } }, "workers": { "total": 2.793907304995628, "count": 232809, "self": 0.0, "children": { "worker_root": { "total": 2454.633517909002, "count": 232809, "is_parallel": true, "self": 1204.7696014649828, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000954228000182411, "count": 1, "is_parallel": true, "self": 0.00027536600009625545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006788620000861556, "count": 2, "is_parallel": true, "self": 0.0006788620000861556 } } }, "UnityEnvironment.step": { "total": 0.029411014999823237, "count": 1, "is_parallel": true, "self": 0.00036435099968912255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020600000016202102, "count": 1, "is_parallel": true, "self": 0.00020600000016202102 }, "communicator.exchange": { "total": 0.02809961100001601, "count": 1, "is_parallel": true, "self": 0.02809961100001601 }, "steps_from_proto": { "total": 0.0007410529999560822, "count": 1, "is_parallel": true, "self": 0.00020355900005597505, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005374939999001072, "count": 2, "is_parallel": true, "self": 0.0005374939999001072 } } } } } } }, "UnityEnvironment.step": { "total": 1249.8639164440192, "count": 232808, "is_parallel": true, "self": 37.158727970841255, "children": { "UnityEnvironment._generate_step_input": { "total": 81.40401443088399, "count": 232808, "is_parallel": true, "self": 81.40401443088399 }, "communicator.exchange": { "total": 1041.6905837182665, "count": 232808, "is_parallel": true, "self": 1041.6905837182665 }, "steps_from_proto": { "total": 89.6105903240275, "count": 232808, "is_parallel": true, "self": 33.51872433707649, "children": { "_process_rank_one_or_two_observation": { "total": 56.09186598695101, "count": 465616, "is_parallel": true, "self": 56.09186598695101 } } } } } } } } } } }, "trainer_advance": { "total": 501.4859815159964, "count": 232809, "self": 6.519965613941849, "children": { "process_trajectory": { "total": 162.18107286105328, "count": 232809, "self": 160.91937127205279, "children": { "RLTrainer._checkpoint": { "total": 1.261701589000495, "count": 10, "self": 1.261701589000495 } } }, "_update_policy": { "total": 332.78494304100127, "count": 97, "self": 266.2886560600184, "children": { "TorchPPOOptimizer.update": { "total": 66.49628698098286, "count": 2910, "self": 66.49628698098286 } } } } } } }, "trainer_threads": { "total": 1.190000148199033e-06, "count": 1, "self": 1.190000148199033e-06 }, "TrainerController._save_models": { "total": 0.1169427180002458, "count": 1, "self": 0.0018806839998433134, "children": { "RLTrainer._checkpoint": { "total": 0.11506203400040249, "count": 1, "self": 0.11506203400040249 } } } } } } }