{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8233461976051331, "min": 0.8233461976051331, "max": 2.8677613735198975, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7825.08203125, "min": 7825.08203125, "max": 29274.107421875, "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": 13.117866516113281, "min": 0.4105920195579529, "max": 13.117866516113281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2557.98388671875, "min": 79.65485382080078, "max": 2650.338623046875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06978037935001409, "min": 0.05965667879240309, "max": 0.07736513846041407, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27912151740005636, "min": 0.23862671516961237, "max": 0.35676943285701174, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19669648161267533, "min": 0.1415417692007716, "max": 0.30647423001481033, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7867859264507013, "min": 0.5661670768030864, "max": 1.3546357373980915, "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": 26.113636363636363, "min": 3.9545454545454546, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1149.0, "min": 174.0, "max": 1398.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.113636363636363, "min": 3.9545454545454546, "max": 26.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1149.0, "min": 174.0, "max": 1398.0, "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": "1739905705", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739906282" }, "total": 576.546201494, "count": 1, "self": 0.586991524000041, "children": { "run_training.setup": { "total": 0.03252286500003265, "count": 1, "self": 0.03252286500003265 }, "TrainerController.start_learning": { "total": 575.9266871049999, "count": 1, "self": 0.6185150240128223, "children": { "TrainerController._reset_env": { "total": 3.150508636999973, "count": 1, "self": 3.150508636999973 }, "TrainerController.advance": { "total": 572.0672725759872, "count": 18192, "self": 0.6475348969971719, "children": { "env_step": { "total": 396.7036380419907, "count": 18192, "self": 335.43480937998453, "children": { "SubprocessEnvManager._take_step": { "total": 60.90442913200377, "count": 18192, "self": 2.0790490220173865, "children": { "TorchPolicy.evaluate": { "total": 58.825380109986384, "count": 18192, "self": 58.825380109986384 } } }, "workers": { "total": 0.36439953000240166, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 573.9340573750005, "count": 18192, "is_parallel": true, "self": 284.162969747996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007351965999987442, "count": 1, "is_parallel": true, "self": 0.005283774000020003, "children": { "_process_rank_one_or_two_observation": { "total": 0.002068191999967439, "count": 10, "is_parallel": true, "self": 0.002068191999967439 } } }, "UnityEnvironment.step": { "total": 0.041989191000027404, "count": 1, "is_parallel": true, "self": 0.0006984299999999166, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045234399999571906, "count": 1, "is_parallel": true, "self": 0.00045234399999571906 }, "communicator.exchange": { "total": 0.038328512000020964, "count": 1, "is_parallel": true, "self": 0.038328512000020964 }, "steps_from_proto": { "total": 0.0025099050000108036, "count": 1, "is_parallel": true, "self": 0.000618882000026133, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018910229999846706, "count": 10, "is_parallel": true, "self": 0.0018910229999846706 } } } } } } }, "UnityEnvironment.step": { "total": 289.77108762700453, "count": 18191, "is_parallel": true, "self": 13.787158328003159, "children": { "UnityEnvironment._generate_step_input": { "total": 7.465394857994681, "count": 18191, "is_parallel": true, "self": 7.465394857994681 }, "communicator.exchange": { "total": 227.12657508200374, "count": 18191, "is_parallel": true, "self": 227.12657508200374 }, "steps_from_proto": { "total": 41.39195935900295, "count": 18191, "is_parallel": true, "self": 8.043786597028543, "children": { "_process_rank_one_or_two_observation": { "total": 33.34817276197441, "count": 181910, "is_parallel": true, "self": 33.34817276197441 } } } } } } } } } } }, "trainer_advance": { "total": 174.71609963699927, "count": 18192, "self": 0.8187407099987922, "children": { "process_trajectory": { "total": 32.09351841100016, "count": 18192, "self": 31.64779832900018, "children": { "RLTrainer._checkpoint": { "total": 0.4457200819999798, "count": 4, "self": 0.4457200819999798 } } }, "_update_policy": { "total": 141.80384051600032, "count": 90, "self": 49.58965937699992, "children": { "TorchPPOOptimizer.update": { "total": 92.2141811390004, "count": 4587, "self": 92.2141811390004 } } } } } } }, "trainer_threads": { "total": 1.0649999921952258e-06, "count": 1, "self": 1.0649999921952258e-06 }, "TrainerController._save_models": { "total": 0.09038980299999366, "count": 1, "self": 0.0013924549999728697, "children": { "RLTrainer._checkpoint": { "total": 0.08899734800002079, "count": 1, "self": 0.08899734800002079 } } } } } } }