{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.891093909740448, "min": 0.891093909740448, "max": 2.865125894546509, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8517.966796875, "min": 8517.966796875, "max": 29373.26953125, "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": 12.81756591796875, "min": 0.3555353283882141, "max": 12.81756591796875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.42529296875, "min": 68.9738540649414, "max": 2608.96875, "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": 0.07187324439748373, "min": 0.061529279315936054, "max": 0.07440341325093279, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2874929775899349, "min": 0.24611711726374422, "max": 0.37201706625466396, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19982142563836247, "min": 0.12421966193234729, "max": 0.27698463049589417, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7992857025534499, "min": 0.49687864772938917, "max": 1.384923152479471, "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": 25.25, "min": 3.659090909090909, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 161.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.659090909090909, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 161.0, "max": 1381.0, "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": "1720646320", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720646769" }, "total": 449.186135848, "count": 1, "self": 0.43613982100004023, "children": { "run_training.setup": { "total": 0.059547864999956346, "count": 1, "self": 0.059547864999956346 }, "TrainerController.start_learning": { "total": 448.690448162, "count": 1, "self": 0.5594309020016226, "children": { "TrainerController._reset_env": { "total": 2.8746164149999913, "count": 1, "self": 2.8746164149999913 }, "TrainerController.advance": { "total": 445.15973843599835, "count": 18202, "self": 0.2602770899912912, "children": { "env_step": { "total": 444.89946134600706, "count": 18202, "self": 289.1451179620001, "children": { "SubprocessEnvManager._take_step": { "total": 155.48015145000704, "count": 18202, "self": 1.5026550020093623, "children": { "TorchPolicy.evaluate": { "total": 153.97749644799768, "count": 18202, "self": 153.97749644799768 } } }, "workers": { "total": 0.2741919339999299, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 447.3922264660082, "count": 18202, "is_parallel": true, "self": 227.4278651380036, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005108687000017653, "count": 1, "is_parallel": true, "self": 0.0033218840000017735, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017868030000158797, "count": 10, "is_parallel": true, "self": 0.0017868030000158797 } } }, "UnityEnvironment.step": { "total": 0.043518272000028446, "count": 1, "is_parallel": true, "self": 0.0008107730000119773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042526999999381587, "count": 1, "is_parallel": true, "self": 0.00042526999999381587 }, "communicator.exchange": { "total": 0.04022408999998106, "count": 1, "is_parallel": true, "self": 0.04022408999998106 }, "steps_from_proto": { "total": 0.0020581390000415922, "count": 1, "is_parallel": true, "self": 0.0003899319999618456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016682070000797466, "count": 10, "is_parallel": true, "self": 0.0016682070000797466 } } } } } } }, "UnityEnvironment.step": { "total": 219.9643613280046, "count": 18201, "is_parallel": true, "self": 10.121557835014471, "children": { "UnityEnvironment._generate_step_input": { "total": 5.295237722000479, "count": 18201, "is_parallel": true, "self": 5.295237722000479 }, "communicator.exchange": { "total": 170.67954013599592, "count": 18201, "is_parallel": true, "self": 170.67954013599592 }, "steps_from_proto": { "total": 33.86802563499373, "count": 18201, "is_parallel": true, "self": 6.357951148988491, "children": { "_process_rank_one_or_two_observation": { "total": 27.510074486005237, "count": 182010, "is_parallel": true, "self": 27.510074486005237 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020174899998437468, "count": 1, "self": 0.00020174899998437468, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 439.5145207350035, "count": 670092, "is_parallel": true, "self": 14.351053841977773, "children": { "process_trajectory": { "total": 244.51419271202553, "count": 670092, "is_parallel": true, "self": 243.81742780702552, "children": { "RLTrainer._checkpoint": { "total": 0.6967649050000091, "count": 4, "is_parallel": true, "self": 0.6967649050000091 } } }, "_update_policy": { "total": 180.64927418100018, "count": 90, "is_parallel": true, "self": 56.04667603100387, "children": { "TorchPPOOptimizer.update": { "total": 124.60259814999631, "count": 4587, "is_parallel": true, "self": 124.60259814999631 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09646066000004794, "count": 1, "self": 0.0009704680001050292, "children": { "RLTrainer._checkpoint": { "total": 0.09549019199994291, "count": 1, "self": 0.09549019199994291 } } } } } } }