{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8833903670310974, "min": 0.8833903670310974, "max": 2.844938278198242, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8473.48046875, "min": 8473.48046875, "max": 29135.01171875, "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": 13.284790992736816, "min": 0.4931192398071289, "max": 13.349401473999023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2590.5341796875, "min": 95.66513061523438, "max": 2723.27783203125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06640885960796902, "min": 0.06242731894027469, "max": 0.07238078322492691, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2656354384318761, "min": 0.2503646752778235, "max": 0.36054516274786746, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20126332829103752, "min": 0.12896142220946358, "max": 0.29486485418151404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8050533131641501, "min": 0.5158456888378543, "max": 1.4743242709075701, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000009e-06, "min": 8.082097306000009e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2328389224000035e-05, "min": 3.2328389224000035e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999998, "min": 0.10269399999999998, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4107759999999999, "min": 0.4107759999999999, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.113636363636363, "min": 4.0, "max": 26.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1149.0, "min": 176.0, "max": 1453.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.113636363636363, "min": 4.0, "max": 26.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1149.0, "min": 176.0, "max": 1453.0, "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": "1724333857", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724334346" }, "total": 489.53835439700015, "count": 1, "self": 0.426320270999895, "children": { "run_training.setup": { "total": 0.05348195800024769, "count": 1, "self": 0.05348195800024769 }, "TrainerController.start_learning": { "total": 489.058552168, "count": 1, "self": 0.5278732290225889, "children": { "TrainerController._reset_env": { "total": 2.044195228999797, "count": 1, "self": 2.044195228999797 }, "TrainerController.advance": { "total": 486.3820269959774, "count": 18207, "self": 0.24879356395740615, "children": { "env_step": { "total": 486.13323343202, "count": 18207, "self": 332.603935729986, "children": { "SubprocessEnvManager._take_step": { "total": 153.27051585499703, "count": 18207, "self": 1.3964455650248055, "children": { "TorchPolicy.evaluate": { "total": 151.87407028997222, "count": 18207, "self": 151.87407028997222 } } }, "workers": { "total": 0.25878184703697116, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 487.9227121609715, "count": 18207, "is_parallel": true, "self": 280.5865455109865, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002134323000063887, "count": 1, "is_parallel": true, "self": 0.0006300740001279337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015042489999359532, "count": 10, "is_parallel": true, "self": 0.0015042489999359532 } } }, "UnityEnvironment.step": { "total": 0.037524909999774536, "count": 1, "is_parallel": true, "self": 0.0006427270000131102, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040964099980556057, "count": 1, "is_parallel": true, "self": 0.00040964099980556057 }, "communicator.exchange": { "total": 0.03454224500001146, "count": 1, "is_parallel": true, "self": 0.03454224500001146 }, "steps_from_proto": { "total": 0.001930296999944403, "count": 1, "is_parallel": true, "self": 0.0003812010004367039, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015490959995076992, "count": 10, "is_parallel": true, "self": 0.0015490959995076992 } } } } } } }, "UnityEnvironment.step": { "total": 207.336166649985, "count": 18206, "is_parallel": true, "self": 9.727830612991966, "children": { "UnityEnvironment._generate_step_input": { "total": 5.160190115035675, "count": 18206, "is_parallel": true, "self": 5.160190115035675 }, "communicator.exchange": { "total": 160.59311277697907, "count": 18206, "is_parallel": true, "self": 160.59311277697907 }, "steps_from_proto": { "total": 31.85503314497828, "count": 18206, "is_parallel": true, "self": 5.938592139966659, "children": { "_process_rank_one_or_two_observation": { "total": 25.91644100501162, "count": 182060, "is_parallel": true, "self": 25.91644100501162 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001603770001565863, "count": 1, "self": 0.0001603770001565863, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 480.955770004085, "count": 644090, "is_parallel": true, "self": 13.637962203492862, "children": { "process_trajectory": { "total": 231.8968412825916, "count": 644090, "is_parallel": true, "self": 230.95321552759196, "children": { "RLTrainer._checkpoint": { "total": 0.9436257549996299, "count": 4, "is_parallel": true, "self": 0.9436257549996299 } } }, "_update_policy": { "total": 235.42096651800057, "count": 90, "is_parallel": true, "self": 80.71888793399694, "children": { "TorchPPOOptimizer.update": { "total": 154.70207858400363, "count": 7645, "is_parallel": true, "self": 154.70207858400363 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1042963370000507, "count": 1, "self": 0.0010795800003506884, "children": { "RLTrainer._checkpoint": { "total": 0.10321675699970001, "count": 1, "self": 0.10321675699970001 } } } } } } }