{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4100329875946045, "min": 1.4100329875946045, "max": 1.4102675914764404, "count": 4 }, "Huggy.Policy.Entropy.sum": { "value": 71471.75, "min": 21591.197265625, "max": 71471.75, "count": 4 }, "Huggy.Environment.EpisodeLength.mean": { "value": 71.27705627705627, "min": 67.03791469194313, "max": 71.50289855072464, "count": 4 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49395.0, "min": 14145.0, "max": 49395.0, "count": 4 }, "Huggy.Step.mean": { "value": 1999968.0, "min": 1849961.0, "max": 1999968.0, "count": 4 }, "Huggy.Step.sum": { "value": 1999968.0, "min": 1849961.0, "max": 1999968.0, "count": 4 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.52115535736084, "min": 2.4745731353759766, "max": 2.52115535736084, "count": 4 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1747.16064453125, "min": 519.6603393554688, "max": 1813.781005859375, "count": 4 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.984487837183183, "min": 3.6954602970963433, "max": 3.984487837183183, "count": 4 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2761.250071167946, "min": 776.0466623902321, "max": 2847.15776515007, "count": 4 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.984487837183183, "min": 3.6954602970963433, "max": 3.984487837183183, "count": 4 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2761.250071167946, "min": 776.0466623902321, "max": 2847.15776515007, "count": 4 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018050915261604433, "min": 0.015791929670376702, "max": 0.018050915261604433, "count": 3 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03610183052320887, "min": 0.031583859340753404, "max": 0.04770719376610941, "count": 3 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06470611660430829, "min": 0.05690601004494561, "max": 0.068085677921772, "count": 3 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.12941223320861658, "min": 0.12941223320861658, "max": 0.17071803013483683, "count": 3 }, "Huggy.Policy.LearningRate.mean": { "value": 4.580573473175012e-06, "min": 4.580573473175012e-06, "max": 1.8479343840249998e-05, "count": 3 }, "Huggy.Policy.LearningRate.sum": { "value": 9.161146946350024e-06, "min": 9.161146946350024e-06, "max": 5.543803152074999e-05, "count": 3 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10152682500000003, "min": 0.10152682500000003, "max": 0.10615975000000001, "count": 3 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20305365000000006, "min": 0.20305365000000006, "max": 0.31847925000000005, "count": 3 }, "Huggy.Policy.Beta.mean": { "value": 8.618856750000021e-05, "min": 8.618856750000021e-05, "max": 0.0003173715250000002, "count": 3 }, "Huggy.Policy.Beta.sum": { "value": 0.00017237713500000042, "min": 0.00017237713500000042, "max": 0.0009521145750000005, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1748948235", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748948603" }, "total": 367.3712024289998, "count": 1, "self": 0.5780116860005364, "children": { "run_training.setup": { "total": 0.038767383999584126, "count": 1, "self": 0.038767383999584126 }, "TrainerController.start_learning": { "total": 366.7544233589997, "count": 1, "self": 0.7246463169794879, "children": { "TrainerController._reset_env": { "total": 3.4544047100007447, "count": 1, "self": 3.4544047100007447 }, "TrainerController.advance": { "total": 362.38045540001986, "count": 19547, "self": 0.7236204119199101, "children": { "env_step": { "total": 247.6992580441365, "count": 19547, "self": 209.30916779605104, "children": { "SubprocessEnvManager._take_step": { "total": 37.9436065271002, "count": 19547, "self": 2.6303886172645434, "children": { "TorchPolicy.evaluate": { "total": 35.31321790983566, "count": 18438, "self": 35.31321790983566 } } }, "workers": { "total": 0.44648372098527034, "count": 19547, "self": 0.0, "children": { "worker_root": { "total": 365.2245978869614, "count": 19547, "is_parallel": true, "self": 197.753486844882, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011185620005562669, "count": 1, "is_parallel": true, "self": 0.0003524189996824134, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007661430008738535, "count": 2, "is_parallel": true, "self": 0.0007661430008738535 } } }, "UnityEnvironment.step": { "total": 0.03578710600049817, "count": 1, "is_parallel": true, "self": 0.0003367179997439962, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021578999985649716, "count": 1, "is_parallel": true, "self": 0.00021578999985649716 }, "communicator.exchange": { "total": 0.03425108900046325, "count": 1, "is_parallel": true, "self": 0.03425108900046325 }, "steps_from_proto": { "total": 0.0009835090004344238, "count": 1, "is_parallel": true, "self": 0.00038915299955988303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005943560008745408, "count": 2, "is_parallel": true, "self": 0.0005943560008745408 } } } } } } }, "UnityEnvironment.step": { "total": 167.47111104207943, "count": 19546, "is_parallel": true, "self": 4.99152768800559, "children": { "UnityEnvironment._generate_step_input": { "total": 9.292093475965885, "count": 19546, "is_parallel": true, "self": 9.292093475965885 }, "communicator.exchange": { "total": 142.02670787710667, "count": 19546, "is_parallel": true, "self": 142.02670787710667 }, "steps_from_proto": { "total": 11.16078200100128, "count": 19546, "is_parallel": true, "self": 3.591538893912002, "children": { "_process_rank_one_or_two_observation": { "total": 7.569243107089278, "count": 39092, "is_parallel": true, "self": 7.569243107089278 } } } } } } } } } } }, "trainer_advance": { "total": 113.95757694396343, "count": 19547, "self": 1.067398576922642, "children": { "process_trajectory": { "total": 24.25657740404131, "count": 19547, "self": 24.108444826042614, "children": { "RLTrainer._checkpoint": { "total": 0.14813257799869461, "count": 1, "self": 0.14813257799869461 } } }, "_update_policy": { "total": 88.63360096299948, "count": 7, "self": 23.25822348899419, "children": { "TorchPPOOptimizer.update": { "total": 65.37537747400529, "count": 210, "self": 65.37537747400529 } } } } } } }, "trainer_threads": { "total": 9.870000212686136e-07, "count": 1, "self": 9.870000212686136e-07 }, "TrainerController._save_models": { "total": 0.1949159449995932, "count": 1, "self": 0.0036575739995896583, "children": { "RLTrainer._checkpoint": { "total": 0.19125837100000354, "count": 1, "self": 0.19125837100000354 } } } } } } }