{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0075597763061523, "min": 0.9888164401054382, "max": 2.8772897720336914, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9664.513671875, "min": 9664.513671875, "max": 29561.275390625, "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": 12.777436256408691, "min": 0.222859725356102, "max": 12.77798843383789, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2491.60009765625, "min": 43.23478698730469, "max": 2604.04296875, "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": 0.06386485690075229, "min": 0.060953700644256294, "max": 0.07627785622254105, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25545942760300916, "min": 0.24413478609137967, "max": 0.36802036703881513, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19827498948457195, "min": 0.12302084668429897, "max": 0.275323733541311, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7930999579382878, "min": 0.49208338673719587, "max": 1.3416651428914537, "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": 25.045454545454547, "min": 3.5, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 154.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.5, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 154.0, "max": 1375.0, "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": "1726701890", "python_version": "3.10.14 (main, Apr 17 2024, 00:00:00) [GCC 13.2.1 20240316 (Red Hat 13.2.1-7)]", "command_line_arguments": "/home/michael/Repo/DeepRLCourse/venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+rocm6.1", "numpy_version": "1.23.5", "end_time_seconds": "1726702058" }, "total": 167.53934326098533, "count": 1, "self": 0.26778159698005766, "children": { "run_training.setup": { "total": 0.021278937987517565, "count": 1, "self": 0.021278937987517565 }, "TrainerController.start_learning": { "total": 167.25028272601776, "count": 1, "self": 0.23624624364310876, "children": { "TrainerController._reset_env": { "total": 0.7836555470130406, "count": 1, "self": 0.7836555470130406 }, "TrainerController.advance": { "total": 166.19833265733905, "count": 18207, "self": 0.11416489214752801, "children": { "env_step": { "total": 166.08416776519152, "count": 18207, "self": 127.47390131663997, "children": { "SubprocessEnvManager._take_step": { "total": 38.494358129333705, "count": 18207, "self": 0.5504380966885947, "children": { "TorchPolicy.evaluate": { "total": 37.94392003264511, "count": 18207, "self": 37.94392003264511 } } }, "workers": { "total": 0.11590831921785139, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 166.98606126121012, "count": 18207, "is_parallel": true, "self": 79.76250455266563, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014897279907017946, "count": 1, "is_parallel": true, "self": 0.0004413939896039665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010483340010978281, "count": 10, "is_parallel": true, "self": 0.0010483340010978281 } } }, "UnityEnvironment.step": { "total": 0.012972844007890671, "count": 1, "is_parallel": true, "self": 0.0001961340312846005, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021953199757263064, "count": 1, "is_parallel": true, "self": 0.00021953199757263064 }, "communicator.exchange": { "total": 0.011894930998096243, "count": 1, "is_parallel": true, "self": 0.011894930998096243 }, "steps_from_proto": { "total": 0.0006622469809371978, "count": 1, "is_parallel": true, "self": 0.0001481639628764242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005140830180607736, "count": 10, "is_parallel": true, "self": 0.0005140830180607736 } } } } } } }, "UnityEnvironment.step": { "total": 87.22355670854449, "count": 18206, "is_parallel": true, "self": 3.4383735776355024, "children": { "UnityEnvironment._generate_step_input": { "total": 2.0567247480212245, "count": 18206, "is_parallel": true, "self": 2.0567247480212245 }, "communicator.exchange": { "total": 70.7483777066227, "count": 18206, "is_parallel": true, "self": 70.7483777066227 }, "steps_from_proto": { "total": 10.980080676265061, "count": 18206, "is_parallel": true, "self": 2.2012714119045995, "children": { "_process_rank_one_or_two_observation": { "total": 8.778809264360461, "count": 182060, "is_parallel": true, "self": 8.778809264360461 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.187802551314235e-05, "count": 1, "self": 4.187802551314235e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 165.7315715236182, "count": 173050, "is_parallel": true, "self": 1.634727385971928, "children": { "process_trajectory": { "total": 90.09302599664079, "count": 173050, "is_parallel": true, "self": 89.86639450563234, "children": { "RLTrainer._checkpoint": { "total": 0.22663149100844748, "count": 4, "is_parallel": true, "self": 0.22663149100844748 } } }, "_update_policy": { "total": 74.00381814100547, "count": 90, "is_parallel": true, "self": 20.567836705042282, "children": { "TorchPPOOptimizer.update": { "total": 53.435981435963186, "count": 4587, "is_parallel": true, "self": 53.435981435963186 } } } } } } } } }, "TrainerController._save_models": { "total": 0.032006399997044355, "count": 1, "self": 0.0007506950059905648, "children": { "RLTrainer._checkpoint": { "total": 0.03125570499105379, "count": 1, "self": 0.03125570499105379 } } } } } } }