{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8922953605651855, "min": 0.8732972145080566, "max": 2.8428292274475098, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8480.375, "min": 8480.375, "max": 29019.6015625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.867924690246582, "min": 0.4987037181854248, "max": 12.867924690246582, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2509.245361328125, "min": 96.74851989746094, "max": 2619.044921875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06943930260532914, "min": 0.06217057364034082, "max": 0.07283962208129394, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27775721042131657, "min": 0.25865773536098263, "max": 0.36419811040646966, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20265349453570797, "min": 0.13551455448545954, "max": 0.3057385783569485, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8106139781428319, "min": 0.5420582179418382, "max": 1.5286928917847427, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.954545454545453, "min": 3.727272727272727, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 164.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.727272727272727, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 164.0, "max": 1402.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1749137880", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749138310" }, "total": 430.1672856309999, "count": 1, "self": 0.6951149729998178, "children": { "run_training.setup": { "total": 0.024331802000006064, "count": 1, "self": 0.024331802000006064 }, "TrainerController.start_learning": { "total": 429.4478388560001, "count": 1, "self": 0.35936790998221113, "children": { "TrainerController._reset_env": { "total": 3.3391275699999596, "count": 1, "self": 3.3391275699999596 }, "TrainerController.advance": { "total": 425.6314161480176, "count": 18192, "self": 0.385795721000477, "children": { "env_step": { "total": 304.7113836920154, "count": 18192, "self": 233.0370000649874, "children": { "SubprocessEnvManager._take_step": { "total": 71.46204329302248, "count": 18192, "self": 1.2647933620243066, "children": { "TorchPolicy.evaluate": { "total": 70.19724993099817, "count": 18192, "self": 70.19724993099817 } } }, "workers": { "total": 0.21234033400548924, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 427.97743346698905, "count": 18192, "is_parallel": true, "self": 223.38679743097396, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00539770300008513, "count": 1, "is_parallel": true, "self": 0.0038001850002729043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015975179998122258, "count": 10, "is_parallel": true, "self": 0.0015975179998122258 } } }, "UnityEnvironment.step": { "total": 0.03920931200002542, "count": 1, "is_parallel": true, "self": 0.0005628980001119999, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044330899993383355, "count": 1, "is_parallel": true, "self": 0.00044330899993383355 }, "communicator.exchange": { "total": 0.036264799000036874, "count": 1, "is_parallel": true, "self": 0.036264799000036874 }, "steps_from_proto": { "total": 0.0019383059999427132, "count": 1, "is_parallel": true, "self": 0.00039153500006250397, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015467709998802093, "count": 10, "is_parallel": true, "self": 0.0015467709998802093 } } } } } } }, "UnityEnvironment.step": { "total": 204.5906360360151, "count": 18191, "is_parallel": true, "self": 9.776943229018343, "children": { "UnityEnvironment._generate_step_input": { "total": 5.463923351993344, "count": 18191, "is_parallel": true, "self": 5.463923351993344 }, "communicator.exchange": { "total": 156.9104932280004, "count": 18191, "is_parallel": true, "self": 156.9104932280004 }, "steps_from_proto": { "total": 32.439276227003006, "count": 18191, "is_parallel": true, "self": 5.864126759000783, "children": { "_process_rank_one_or_two_observation": { "total": 26.575149468002223, "count": 181910, "is_parallel": true, "self": 26.575149468002223 } } } } } } } } } } }, "trainer_advance": { "total": 120.53423673500174, "count": 18192, "self": 0.4416784890030385, "children": { "process_trajectory": { "total": 27.369160335999254, "count": 18192, "self": 26.855431421999242, "children": { "RLTrainer._checkpoint": { "total": 0.5137289140000121, "count": 4, "self": 0.5137289140000121 } } }, "_update_policy": { "total": 92.72339790999945, "count": 90, "self": 37.41942031398946, "children": { "TorchPPOOptimizer.update": { "total": 55.303977596009986, "count": 4587, "self": 55.303977596009986 } } } } } } }, "trainer_threads": { "total": 1.1230001746298512e-06, "count": 1, "self": 1.1230001746298512e-06 }, "TrainerController._save_models": { "total": 0.11792610500015144, "count": 1, "self": 0.001023506000137786, "children": { "RLTrainer._checkpoint": { "total": 0.11690259900001365, "count": 1, "self": 0.11690259900001365 } } } } } } }