{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.818248450756073, "min": 0.818248450756073, "max": 2.833265542984009, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7776.63330078125, "min": 7776.63330078125, "max": 28921.974609375, "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": 12.87984561920166, "min": 0.4199436902999878, "max": 12.87984561920166, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2511.56982421875, "min": 81.46907806396484, "max": 2580.32275390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07089077149501855, "min": 0.06521077611684507, "max": 0.0750741771453071, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2835630859800742, "min": 0.26113441084025374, "max": 0.3698712461462527, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17824178294954346, "min": 0.1469016330974067, "max": 0.28763652417589636, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7129671317981738, "min": 0.5876065323896268, "max": 1.412575007653704, "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": 25.863636363636363, "min": 3.9318181818181817, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1138.0, "min": 173.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.863636363636363, "min": 3.9318181818181817, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1138.0, "min": 173.0, "max": 1408.0, "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": "1737994060", "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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737994492" }, "total": 432.274020995, "count": 1, "self": 0.7439376189998939, "children": { "run_training.setup": { "total": 0.02263244800008124, "count": 1, "self": 0.02263244800008124 }, "TrainerController.start_learning": { "total": 431.507450928, "count": 1, "self": 0.3599304540008461, "children": { "TrainerController._reset_env": { "total": 2.8050440679999156, "count": 1, "self": 2.8050440679999156 }, "TrainerController.advance": { "total": 428.2124001219993, "count": 18192, "self": 0.37125998901024104, "children": { "env_step": { "total": 302.2129840819998, "count": 18192, "self": 229.849019090993, "children": { "SubprocessEnvManager._take_step": { "total": 72.13866476800456, "count": 18192, "self": 1.2604409500120255, "children": { "TorchPolicy.evaluate": { "total": 70.87822381799253, "count": 18192, "self": 70.87822381799253 } } }, "workers": { "total": 0.22530022300225028, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 429.92265259798364, "count": 18192, "is_parallel": true, "self": 229.23311197299438, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005533027000069524, "count": 1, "is_parallel": true, "self": 0.003981024999802685, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015520020002668389, "count": 10, "is_parallel": true, "self": 0.0015520020002668389 } } }, "UnityEnvironment.step": { "total": 0.03672555499997543, "count": 1, "is_parallel": true, "self": 0.0015701020000733479, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045471099997485, "count": 1, "is_parallel": true, "self": 0.00045471099997485 }, "communicator.exchange": { "total": 0.032887107999954424, "count": 1, "is_parallel": true, "self": 0.032887107999954424 }, "steps_from_proto": { "total": 0.001813633999972808, "count": 1, "is_parallel": true, "self": 0.0003516219998118686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014620120001609394, "count": 10, "is_parallel": true, "self": 0.0014620120001609394 } } } } } } }, "UnityEnvironment.step": { "total": 200.68954062498926, "count": 18191, "is_parallel": true, "self": 9.762462172986602, "children": { "UnityEnvironment._generate_step_input": { "total": 5.305538747001492, "count": 18191, "is_parallel": true, "self": 5.305538747001492 }, "communicator.exchange": { "total": 154.73291415799906, "count": 18191, "is_parallel": true, "self": 154.73291415799906 }, "steps_from_proto": { "total": 30.888625547002107, "count": 18191, "is_parallel": true, "self": 5.502909813000883, "children": { "_process_rank_one_or_two_observation": { "total": 25.385715734001224, "count": 181910, "is_parallel": true, "self": 25.385715734001224 } } } } } } } } } } }, "trainer_advance": { "total": 125.62815605098922, "count": 18192, "self": 0.47473789199261773, "children": { "process_trajectory": { "total": 27.399750728997333, "count": 18192, "self": 26.9233125059975, "children": { "RLTrainer._checkpoint": { "total": 0.47643822299983185, "count": 4, "self": 0.47643822299983185 } } }, "_update_policy": { "total": 97.75366742999927, "count": 90, "self": 38.94333522900081, "children": { "TorchPPOOptimizer.update": { "total": 58.81033220099846, "count": 4587, "self": 58.81033220099846 } } } } } } }, "trainer_threads": { "total": 1.32200000280136e-06, "count": 1, "self": 1.32200000280136e-06 }, "TrainerController._save_models": { "total": 0.1300749619999806, "count": 1, "self": 0.0012520039999799337, "children": { "RLTrainer._checkpoint": { "total": 0.12882295800000065, "count": 1, "self": 0.12882295800000065 } } } } } } }