{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9399226307868958, "min": 0.911098301410675, "max": 2.844542980194092, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8933.0244140625, "min": 8933.0244140625, "max": 29037.09375, "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": 12.943323135375977, "min": 0.43677741289138794, "max": 12.943323135375977, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.947998046875, "min": 84.73481750488281, "max": 2627.193603515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0752724973558632, "min": 0.0640348660328777, "max": 0.0752724973558632, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3010899894234528, "min": 0.25629310090252877, "max": 0.36941860446948377, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.202012602385937, "min": 0.14975204336566522, "max": 0.28857568654359556, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.808050409543748, "min": 0.5990081734626609, "max": 1.4428784327179778, "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": 25.5, "min": 4.295454545454546, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 189.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 4.295454545454546, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 189.0, "max": 1406.0, "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": "1775496977", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1775497447" }, "total": 469.74746457300034, "count": 1, "self": 0.48619798999970953, "children": { "run_training.setup": { "total": 0.022435498000049847, "count": 1, "self": 0.022435498000049847 }, "TrainerController.start_learning": { "total": 469.2388310850006, "count": 1, "self": 0.39525449896245846, "children": { "TrainerController._reset_env": { "total": 3.377542497000377, "count": 1, "self": 3.377542497000377 }, "TrainerController.advance": { "total": 465.3854584540368, "count": 18192, "self": 0.43530636413925095, "children": { "env_step": { "total": 340.1662169319561, "count": 18192, "self": 265.33439665899505, "children": { "SubprocessEnvManager._take_step": { "total": 74.59321005000174, "count": 18192, "self": 1.3541411020137275, "children": { "TorchPolicy.evaluate": { "total": 73.23906894798802, "count": 18192, "self": 73.23906894798802 } } }, "workers": { "total": 0.23861022295932344, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 467.5277803010158, "count": 18192, "is_parallel": true, "self": 234.58986215400728, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00451479899993501, "count": 1, "is_parallel": true, "self": 0.002938197000275977, "children": { "_process_rank_one_or_two_observation": { "total": 0.001576601999659033, "count": 10, "is_parallel": true, "self": 0.001576601999659033 } } }, "UnityEnvironment.step": { "total": 0.04124115000013262, "count": 1, "is_parallel": true, "self": 0.0006251060003705788, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040899199984778534, "count": 1, "is_parallel": true, "self": 0.00040899199984778534 }, "communicator.exchange": { "total": 0.038081786000020657, "count": 1, "is_parallel": true, "self": 0.038081786000020657 }, "steps_from_proto": { "total": 0.0021252659998935997, "count": 1, "is_parallel": true, "self": 0.0004271580005479336, "children": { "_process_rank_one_or_two_observation": { "total": 0.001698107999345666, "count": 10, "is_parallel": true, "self": 0.001698107999345666 } } } } } } }, "UnityEnvironment.step": { "total": 232.93791814700853, "count": 18191, "is_parallel": true, "self": 10.73477772203887, "children": { "UnityEnvironment._generate_step_input": { "total": 5.908622948991251, "count": 18191, "is_parallel": true, "self": 5.908622948991251 }, "communicator.exchange": { "total": 175.9170566629523, "count": 18191, "is_parallel": true, "self": 175.9170566629523 }, "steps_from_proto": { "total": 40.37746081302612, "count": 18191, "is_parallel": true, "self": 7.215545413884229, "children": { "_process_rank_one_or_two_observation": { "total": 33.16191539914189, "count": 181910, "is_parallel": true, "self": 33.16191539914189 } } } } } } } } } } }, "trainer_advance": { "total": 124.78393515794141, "count": 18192, "self": 0.47994380101454226, "children": { "process_trajectory": { "total": 28.149311672932527, "count": 18192, "self": 27.71918669593333, "children": { "RLTrainer._checkpoint": { "total": 0.4301249769991955, "count": 4, "self": 0.4301249769991955 } } }, "_update_policy": { "total": 96.15467968399435, "count": 90, "self": 39.42701371901694, "children": { "TorchPPOOptimizer.update": { "total": 56.727665964977405, "count": 4587, "self": 56.727665964977405 } } } } } } }, "trainer_threads": { "total": 9.120003596763127e-07, "count": 1, "self": 9.120003596763127e-07 }, "TrainerController._save_models": { "total": 0.08057472300060908, "count": 1, "self": 0.0007312540010389057, "children": { "RLTrainer._checkpoint": { "total": 0.07984346899957018, "count": 1, "self": 0.07984346899957018 } } } } } } }