{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9094187021255493, "min": 0.9062680602073669, "max": 2.86100172996521, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8703.13671875, "min": 8703.13671875, "max": 29330.990234375, "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": 12.907567024230957, "min": 0.40926918387413025, "max": 12.907567024230957, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2516.9755859375, "min": 79.39822387695312, "max": 2615.575927734375, "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": 0.07635805906465976, "min": 0.06377678062291998, "max": 0.07635805906465976, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.305432236258639, "min": 0.2563516776071457, "max": 0.36598135965480244, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19255309895265338, "min": 0.11362479243532517, "max": 0.2792209448913733, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7702123958106135, "min": 0.45449916974130067, "max": 1.377831920397048, "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": 25.386363636363637, "min": 3.3636363636363638, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 148.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.3636363636363638, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 148.0, "max": 1403.0, "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": "1735208990", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/root/miniconda3/envs/drl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1", "numpy_version": "1.23.5", "end_time_seconds": "1735209352" }, "total": 361.8585792600006, "count": 1, "self": 0.32353066699943156, "children": { "run_training.setup": { "total": 0.016393618000620336, "count": 1, "self": 0.016393618000620336 }, "TrainerController.start_learning": { "total": 361.5186549750006, "count": 1, "self": 0.6104526289554997, "children": { "TrainerController._reset_env": { "total": 4.149019462000069, "count": 1, "self": 4.149019462000069 }, "TrainerController.advance": { "total": 356.71385173004455, "count": 18204, "self": 0.26460164307445666, "children": { "env_step": { "total": 356.4492500869701, "count": 18204, "self": 263.96654813897294, "children": { "SubprocessEnvManager._take_step": { "total": 92.1999077909586, "count": 18204, "self": 1.3662182699226832, "children": { "TorchPolicy.evaluate": { "total": 90.83368952103592, "count": 18204, "self": 90.83368952103592 } } }, "workers": { "total": 0.28279415703855193, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 360.6300417930797, "count": 18204, "is_parallel": true, "self": 171.49642246407257, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017535309998493176, "count": 1, "is_parallel": true, "self": 0.0005641159987135325, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011894150011357851, "count": 10, "is_parallel": true, "self": 0.0011894150011357851 } } }, "UnityEnvironment.step": { "total": 0.02643722599987086, "count": 1, "is_parallel": true, "self": 0.0003781400009756908, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031059199955052463, "count": 1, "is_parallel": true, "self": 0.00031059199955052463 }, "communicator.exchange": { "total": 0.024451494999993884, "count": 1, "is_parallel": true, "self": 0.024451494999993884 }, "steps_from_proto": { "total": 0.0012969989993507625, "count": 1, "is_parallel": true, "self": 0.0002932659999714815, "children": { "_process_rank_one_or_two_observation": { "total": 0.001003732999379281, "count": 10, "is_parallel": true, "self": 0.001003732999379281 } } } } } } }, "UnityEnvironment.step": { "total": 189.13361932900716, "count": 18203, "is_parallel": true, "self": 6.348542761074896, "children": { "UnityEnvironment._generate_step_input": { "total": 4.259044752969203, "count": 18203, "is_parallel": true, "self": 4.259044752969203 }, "communicator.exchange": { "total": 159.22925724402376, "count": 18203, "is_parallel": true, "self": 159.22925724402376 }, "steps_from_proto": { "total": 19.296774570939306, "count": 18203, "is_parallel": true, "self": 4.305243835106921, "children": { "_process_rank_one_or_two_observation": { "total": 14.991530735832384, "count": 182030, "is_parallel": true, "self": 14.991530735832384 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001585159998285235, "count": 1, "self": 0.0001585159998285235, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 355.5102598479989, "count": 210599, "is_parallel": true, "self": 4.3694417150991285, "children": { "process_trajectory": { "total": 197.99277340189656, "count": 210599, "is_parallel": true, "self": 197.52658856489688, "children": { "RLTrainer._checkpoint": { "total": 0.4661848369996733, "count": 4, "is_parallel": true, "self": 0.4661848369996733 } } }, "_update_policy": { "total": 153.1480447310032, "count": 90, "is_parallel": true, "self": 29.73257070400723, "children": { "TorchPPOOptimizer.update": { "total": 123.41547402699598, "count": 4587, "is_parallel": true, "self": 123.41547402699598 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0451726380006221, "count": 1, "self": 0.0008058430003075046, "children": { "RLTrainer._checkpoint": { "total": 0.044366795000314596, "count": 1, "self": 0.044366795000314596 } } } } } } }