{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9750540852546692, "min": 0.9750540852546692, "max": 2.8699076175689697, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9309.81640625, "min": 9309.81640625, "max": 29548.568359375, "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": 12.727063179016113, "min": 0.3127080500125885, "max": 12.727063179016113, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2481.77734375, "min": 60.66536331176758, "max": 2590.387451171875, "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": 0.07136390286487036, "min": 0.05998318245567098, "max": 0.07413812781091753, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28545561145948145, "min": 0.23993272982268393, "max": 0.3553414421907042, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22352900575189028, "min": 0.10730891930414183, "max": 0.28717295014682936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8941160230075611, "min": 0.4292356772165673, "max": 1.3967360509376903, "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": 25.15909090909091, "min": 2.909090909090909, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 128.0, "max": 1381.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 2.909090909090909, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 128.0, "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": "1730263026", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730263628" }, "total": 602.410200684, "count": 1, "self": 0.5502740869998206, "children": { "run_training.setup": { "total": 0.06799128300002621, "count": 1, "self": 0.06799128300002621 }, "TrainerController.start_learning": { "total": 601.791935314, "count": 1, "self": 0.8565264750006918, "children": { "TrainerController._reset_env": { "total": 7.102622779000001, "count": 1, "self": 7.102622779000001 }, "TrainerController.advance": { "total": 593.7424778149995, "count": 18204, "self": 0.42200121099608623, "children": { "env_step": { "total": 593.3204766040034, "count": 18204, "self": 457.4551682659982, "children": { "SubprocessEnvManager._take_step": { "total": 135.46722750699763, "count": 18204, "self": 2.3856758460029255, "children": { "TorchPolicy.evaluate": { "total": 133.0815516609947, "count": 18204, "self": 133.0815516609947 } } }, "workers": { "total": 0.398080831007519, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 599.7928024159996, "count": 18204, "is_parallel": true, "self": 289.5610951199916, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002811276000045382, "count": 1, "is_parallel": true, "self": 0.000859062000074573, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019522139999708088, "count": 10, "is_parallel": true, "self": 0.0019522139999708088 } } }, "UnityEnvironment.step": { "total": 0.10371391299997867, "count": 1, "is_parallel": true, "self": 0.0008428579999417707, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004969610000102875, "count": 1, "is_parallel": true, "self": 0.0004969610000102875 }, "communicator.exchange": { "total": 0.09689623299999539, "count": 1, "is_parallel": true, "self": 0.09689623299999539 }, "steps_from_proto": { "total": 0.0054778610000312256, "count": 1, "is_parallel": true, "self": 0.000519920000044749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0049579409999864765, "count": 10, "is_parallel": true, "self": 0.0049579409999864765 } } } } } } }, "UnityEnvironment.step": { "total": 310.23170729600804, "count": 18203, "is_parallel": true, "self": 14.639752945008013, "children": { "UnityEnvironment._generate_step_input": { "total": 7.459156354998072, "count": 18203, "is_parallel": true, "self": 7.459156354998072 }, "communicator.exchange": { "total": 244.73958316700163, "count": 18203, "is_parallel": true, "self": 244.73958316700163 }, "steps_from_proto": { "total": 43.39321482900033, "count": 18203, "is_parallel": true, "self": 8.484331210995265, "children": { "_process_rank_one_or_two_observation": { "total": 34.90888361800506, "count": 182030, "is_parallel": true, "self": 34.90888361800506 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017511199996533833, "count": 1, "self": 0.00017511199996533833, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 586.953135447004, "count": 764472, "is_parallel": true, "self": 17.06788920292513, "children": { "process_trajectory": { "total": 312.45867027107914, "count": 764472, "is_parallel": true, "self": 311.32127748807915, "children": { "RLTrainer._checkpoint": { "total": 1.1373927829999957, "count": 4, "is_parallel": true, "self": 1.1373927829999957 } } }, "_update_policy": { "total": 257.4265759729997, "count": 90, "is_parallel": true, "self": 73.95207107099776, "children": { "TorchPPOOptimizer.update": { "total": 183.4745049020019, "count": 4587, "is_parallel": true, "self": 183.4745049020019 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09013313299999481, "count": 1, "self": 0.0011429550000912059, "children": { "RLTrainer._checkpoint": { "total": 0.08899017799990361, "count": 1, "self": 0.08899017799990361 } } } } } } }