{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7473859786987305, "min": 0.698795735836029, "max": 2.8428192138671875, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7103.15625, "min": 7033.9423828125, "max": 29019.498046875, "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": 12.030961990356445, "min": 0.29024022817611694, "max": 12.042171478271484, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2346.03759765625, "min": 56.306602478027344, "max": 2456.60302734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06998432599014931, "min": 0.06402944147035561, "max": 0.07360665393792384, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27993730396059724, "min": 0.2661517856730486, "max": 0.36803326968961925, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1991756586175339, "min": 0.11212130526409429, "max": 0.2997071329577296, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7967026344701356, "min": 0.44848522105637717, "max": 1.4189729772362054, "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.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.Environment.CumulativeReward.mean": { "value": 23.40909090909091, "min": 3.477272727272727, "max": 23.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1030.0, "min": 153.0, "max": 1288.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.40909090909091, "min": 3.477272727272727, "max": 23.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1030.0, "min": 153.0, "max": 1288.0, "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": "1742614664", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742615095" }, "total": 430.23553539, "count": 1, "self": 0.4295410749999746, "children": { "run_training.setup": { "total": 0.030528421999974853, "count": 1, "self": 0.030528421999974853 }, "TrainerController.start_learning": { "total": 429.77546589300005, "count": 1, "self": 0.347077543998239, "children": { "TrainerController._reset_env": { "total": 3.8269495590000133, "count": 1, "self": 3.8269495590000133 }, "TrainerController.advance": { "total": 425.51323378200175, "count": 18192, "self": 0.3734072450064332, "children": { "env_step": { "total": 300.61379729400073, "count": 18192, "self": 228.80132772397815, "children": { "SubprocessEnvManager._take_step": { "total": 71.60223894100761, "count": 18192, "self": 1.2422068320050812, "children": { "TorchPolicy.evaluate": { "total": 70.36003210900253, "count": 18192, "self": 70.36003210900253 } } }, "workers": { "total": 0.2102306290149727, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 428.4454572220003, "count": 18192, "is_parallel": true, "self": 227.38588536401312, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006838531000084913, "count": 1, "is_parallel": true, "self": 0.00452317400015545, "children": { "_process_rank_one_or_two_observation": { "total": 0.002315356999929463, "count": 10, "is_parallel": true, "self": 0.002315356999929463 } } }, "UnityEnvironment.step": { "total": 0.03434025199999269, "count": 1, "is_parallel": true, "self": 0.000571638999872448, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039420699999936915, "count": 1, "is_parallel": true, "self": 0.00039420699999936915 }, "communicator.exchange": { "total": 0.03150537300007272, "count": 1, "is_parallel": true, "self": 0.03150537300007272 }, "steps_from_proto": { "total": 0.001869033000048148, "count": 1, "is_parallel": true, "self": 0.00037185500013947603, "children": { "_process_rank_one_or_two_observation": { "total": 0.001497177999908672, "count": 10, "is_parallel": true, "self": 0.001497177999908672 } } } } } } }, "UnityEnvironment.step": { "total": 201.05957185798718, "count": 18191, "is_parallel": true, "self": 9.7697990409672, "children": { "UnityEnvironment._generate_step_input": { "total": 5.258001112009879, "count": 18191, "is_parallel": true, "self": 5.258001112009879 }, "communicator.exchange": { "total": 154.86538953700926, "count": 18191, "is_parallel": true, "self": 154.86538953700926 }, "steps_from_proto": { "total": 31.166382168000837, "count": 18191, "is_parallel": true, "self": 5.463314938001304, "children": { "_process_rank_one_or_two_observation": { "total": 25.703067229999533, "count": 181910, "is_parallel": true, "self": 25.703067229999533 } } } } } } } } } } }, "trainer_advance": { "total": 124.52602924299458, "count": 18192, "self": 0.45260140598861653, "children": { "process_trajectory": { "total": 26.71073177300559, "count": 18192, "self": 26.200516266005593, "children": { "RLTrainer._checkpoint": { "total": 0.5102155069999981, "count": 4, "self": 0.5102155069999981 } } }, "_update_policy": { "total": 97.36269606400037, "count": 90, "self": 38.81020596000121, "children": { "TorchPPOOptimizer.update": { "total": 58.55249010399916, "count": 4587, "self": 58.55249010399916 } } } } } } }, "trainer_threads": { "total": 1.040000029206567e-06, "count": 1, "self": 1.040000029206567e-06 }, "TrainerController._save_models": { "total": 0.08820396800001618, "count": 1, "self": 0.0009769520000872944, "children": { "RLTrainer._checkpoint": { "total": 0.08722701599992888, "count": 1, "self": 0.08722701599992888 } } } } } } }