{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4077413082122803, "min": 1.4077413082122803, "max": 1.4235455989837646, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69600.140625, "min": 68248.734375, "max": 78795.2421875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.28571428571429, "min": 78.7156704361874, "max": 384.8538461538462, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48924.0, "min": 48725.0, "max": 50081.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999914.0, "min": 49492.0, "max": 1999914.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999914.0, "min": 49492.0, "max": 1999914.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4658946990966797, "min": -0.007927387952804565, "max": 2.4889934062957764, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1398.162353515625, "min": -1.0226330757141113, "max": 1483.8568115234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.897299460107477, "min": 1.7069435798844625, "max": 3.9313106473960677, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2209.7687938809395, "min": 220.19572180509567, "max": 2369.004542052746, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.897299460107477, "min": 1.7069435798844625, "max": 3.9313106473960677, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2209.7687938809395, "min": 220.19572180509567, "max": 2369.004542052746, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.020558336823564283, "min": 0.01388549273397075, "max": 0.020558336823564283, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.06167501047069285, "min": 0.0277709854679415, "max": 0.06167501047069285, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06005002698964542, "min": 0.023266762557129065, "max": 0.061450071301725175, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18015008096893625, "min": 0.04653352511425813, "max": 0.18435021390517553, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.153748948783329e-06, "min": 3.153748948783329e-06, "max": 0.0002953729515423499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.461246846349987e-06, "min": 9.461246846349987e-06, "max": 0.00084418366860545, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105121666666671, "min": 0.10105121666666671, "max": 0.19845764999999999, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031536500000001, "min": 0.20727225000000002, "max": 0.58139455, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.245571166666661e-05, "min": 6.245571166666661e-05, "max": 0.0049230367350000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018736713499999984, "min": 0.00018736713499999984, "max": 0.014071588045000003, "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": "1736343466", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736345864" }, "total": 2397.90087623, "count": 1, "self": 0.735940596999626, "children": { "run_training.setup": { "total": 0.08698283800003992, "count": 1, "self": 0.08698283800003992 }, "TrainerController.start_learning": { "total": 2397.0779527950003, "count": 1, "self": 4.322980497055596, "children": { "TrainerController._reset_env": { "total": 5.418570149000004, "count": 1, "self": 5.418570149000004 }, "TrainerController.advance": { "total": 2387.1695041909447, "count": 232196, "self": 4.619746278935509, "children": { "env_step": { "total": 1883.069689061983, "count": 232196, "self": 1473.9491136078532, "children": { "SubprocessEnvManager._take_step": { "total": 406.42411316616597, "count": 232196, "self": 15.765035206232255, "children": { "TorchPolicy.evaluate": { "total": 390.6590779599337, "count": 222852, "self": 390.6590779599337 } } }, "workers": { "total": 2.6964622879636977, "count": 232196, "self": 0.0, "children": { "worker_root": { "total": 2389.7041703529517, "count": 232196, "is_parallel": true, "self": 1195.1906539420172, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010264549999874362, "count": 1, "is_parallel": true, "self": 0.0003076959999361861, "children": { "_process_rank_one_or_two_observation": { "total": 0.00071875900005125, "count": 2, "is_parallel": true, "self": 0.00071875900005125 } } }, "UnityEnvironment.step": { "total": 0.028159082000001945, "count": 1, "is_parallel": true, "self": 0.0003946840000139673, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002041770000005272, "count": 1, "is_parallel": true, "self": 0.0002041770000005272 }, "communicator.exchange": { "total": 0.026819341999953394, "count": 1, "is_parallel": true, "self": 0.026819341999953394 }, "steps_from_proto": { "total": 0.0007408790000340559, "count": 1, "is_parallel": true, "self": 0.00019980000001851295, "children": { "_process_rank_one_or_two_observation": { "total": 0.000541079000015543, "count": 2, "is_parallel": true, "self": 0.000541079000015543 } } } } } } }, "UnityEnvironment.step": { "total": 1194.5135164109345, "count": 232195, "is_parallel": true, "self": 37.30260187376575, "children": { "UnityEnvironment._generate_step_input": { "total": 80.53941627011892, "count": 232195, "is_parallel": true, "self": 80.53941627011892 }, "communicator.exchange": { "total": 989.9070340480289, "count": 232195, "is_parallel": true, "self": 989.9070340480289 }, "steps_from_proto": { "total": 86.76446421902102, "count": 232195, "is_parallel": true, "self": 30.85514978810511, "children": { "_process_rank_one_or_two_observation": { "total": 55.90931443091591, "count": 464390, "is_parallel": true, "self": 55.90931443091591 } } } } } } } } } } }, "trainer_advance": { "total": 499.48006885002656, "count": 232196, "self": 6.233541568086821, "children": { "process_trajectory": { "total": 163.61897116593963, "count": 232196, "self": 162.12192225193945, "children": { "RLTrainer._checkpoint": { "total": 1.4970489140001746, "count": 10, "self": 1.4970489140001746 } } }, "_update_policy": { "total": 329.6275561160001, "count": 97, "self": 263.26565055899175, "children": { "TorchPPOOptimizer.update": { "total": 66.36190555700836, "count": 2910, "self": 66.36190555700836 } } } } } } }, "trainer_threads": { "total": 1.2420000530255493e-06, "count": 1, "self": 1.2420000530255493e-06 }, "TrainerController._save_models": { "total": 0.16689671599988287, "count": 1, "self": 0.002968417999909434, "children": { "RLTrainer._checkpoint": { "total": 0.16392829799997344, "count": 1, "self": 0.16392829799997344 } } } } } } }