{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9926164746284485, "min": 0.9926164746284485, "max": 2.8742170333862305, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9488.4208984375, "min": 9488.4208984375, "max": 29434.857421875, "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": 12.971051216125488, "min": 0.4603939652442932, "max": 12.971051216125488, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2529.35498046875, "min": 89.3164291381836, "max": 2607.56689453125, "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.Losses.PolicyLoss.mean": { "value": 0.06815678095054133, "min": 0.0590927433099269, "max": 0.07099707878553412, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2726271238021653, "min": 0.24606094409810952, "max": 0.3505219657176092, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17172309526187532, "min": 0.1351226290856835, "max": 0.31543342277959546, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6868923810475013, "min": 0.540490516342734, "max": 1.5771671138979773, "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.CumulativeReward.mean": { "value": 25.40909090909091, "min": 3.6363636363636362, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 160.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.6363636363636362, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 160.0, "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": "1715296737", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715297252" }, "total": 515.2334347450001, "count": 1, "self": 0.43526630400015165, "children": { "run_training.setup": { "total": 0.055582709000020714, "count": 1, "self": 0.055582709000020714 }, "TrainerController.start_learning": { "total": 514.742585732, "count": 1, "self": 0.7176597569966816, "children": { "TrainerController._reset_env": { "total": 2.829216355999961, "count": 1, "self": 2.829216355999961 }, "TrainerController.advance": { "total": 511.0945165830033, "count": 18200, "self": 0.37153699100929316, "children": { "env_step": { "total": 510.72297959199403, "count": 18200, "self": 337.7543673099936, "children": { "SubprocessEnvManager._take_step": { "total": 172.61164248700396, "count": 18200, "self": 1.7528480579969141, "children": { "TorchPolicy.evaluate": { "total": 170.85879442900705, "count": 18200, "self": 170.85879442900705 } } }, "workers": { "total": 0.3569697949964734, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 513.0338691359949, "count": 18200, "is_parallel": true, "self": 253.8498637169875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005406445000005533, "count": 1, "is_parallel": true, "self": 0.003659141000071031, "children": { "_process_rank_one_or_two_observation": { "total": 0.001747303999934502, "count": 10, "is_parallel": true, "self": 0.001747303999934502 } } }, "UnityEnvironment.step": { "total": 0.04367068400000562, "count": 1, "is_parallel": true, "self": 0.0007875720000356523, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045293800002355056, "count": 1, "is_parallel": true, "self": 0.00045293800002355056 }, "communicator.exchange": { "total": 0.040167387999986204, "count": 1, "is_parallel": true, "self": 0.040167387999986204 }, "steps_from_proto": { "total": 0.002262785999960215, "count": 1, "is_parallel": true, "self": 0.00044681800000034855, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018159679999598666, "count": 10, "is_parallel": true, "self": 0.0018159679999598666 } } } } } } }, "UnityEnvironment.step": { "total": 259.1840054190074, "count": 18199, "is_parallel": true, "self": 11.696345605000033, "children": { "UnityEnvironment._generate_step_input": { "total": 6.205422545994509, "count": 18199, "is_parallel": true, "self": 6.205422545994509 }, "communicator.exchange": { "total": 202.3977658580049, "count": 18199, "is_parallel": true, "self": 202.3977658580049 }, "steps_from_proto": { "total": 38.88447141000796, "count": 18199, "is_parallel": true, "self": 7.6776320300044745, "children": { "_process_rank_one_or_two_observation": { "total": 31.206839380003487, "count": 181990, "is_parallel": true, "self": 31.206839380003487 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015282399999705376, "count": 1, "self": 0.00015282399999705376, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 504.9122626120303, "count": 745004, "is_parallel": true, "self": 15.955341355043117, "children": { "process_trajectory": { "total": 280.8601050039873, "count": 745004, "is_parallel": true, "self": 279.47239095398726, "children": { "RLTrainer._checkpoint": { "total": 1.3877140500000564, "count": 4, "is_parallel": true, "self": 1.3877140500000564 } } }, "_update_policy": { "total": 208.09681625299987, "count": 90, "is_parallel": true, "self": 66.23543080699733, "children": { "TorchPPOOptimizer.update": { "total": 141.86138544600254, "count": 4584, "is_parallel": true, "self": 141.86138544600254 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10104021200004354, "count": 1, "self": 0.0009536840000237135, "children": { "RLTrainer._checkpoint": { "total": 0.10008652800001983, "count": 1, "self": 0.10008652800001983 } } } } } } }