{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0551000833511353, "min": 1.0551000833511353, "max": 2.862008571624756, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10085.701171875, "min": 10085.701171875, "max": 29498.72265625, "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": 12.656046867370605, "min": 0.32267439365386963, "max": 12.656046867370605, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2467.92919921875, "min": 62.59883499145508, "max": 2567.480712890625, "count": 20 }, "SnowballTarget.Policy.RndValueEstimate.mean": { "value": -0.0009955825516954064, "min": -0.03700552135705948, "max": 0.00973495189100504, "count": 20 }, "SnowballTarget.Policy.RndValueEstimate.sum": { "value": -0.19413858652114868, "min": -7.179071426391602, "max": 1.898315668106079, "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": 0.06684095613537447, "min": 0.061452012961358285, "max": 0.07469023812383038, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2673638245414979, "min": 0.24580805184543314, "max": 0.3529809728708785, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.10505503836069621, "min": 0.06902955410837688, "max": 0.14385717073638066, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.42022015344278485, "min": 0.27611821643350754, "max": 0.6739003345662472, "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.Losses.RNDLoss.mean": { "value": 0.004172837361693382, "min": 0.004172837361693382, "max": 0.41886237263679504, "count": 20 }, "SnowballTarget.Losses.RNDLoss.sum": { "value": 0.01669134944677353, "min": 0.01669134944677353, "max": 1.6754494905471802, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.272727272727273, "min": 3.8181818181818183, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 168.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.8181818181818183, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 168.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.RndReward.mean": { "value": 0.004277452380020722, "min": 0.004277452380020722, "max": 0.5791144296950237, "count": 20 }, "SnowballTarget.Policy.RndReward.sum": { "value": 0.18820790472091176, "min": 0.18820790472091176, "max": 25.481034906581044, "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": "1719419975", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719420664" }, "total": 688.6761523559999, "count": 1, "self": 1.0541900560001523, "children": { "run_training.setup": { "total": 0.06820072099981189, "count": 1, "self": 0.06820072099981189 }, "TrainerController.start_learning": { "total": 687.5537615789999, "count": 1, "self": 1.3037707329103796, "children": { "TrainerController._reset_env": { "total": 2.538256335999904, "count": 1, "self": 2.538256335999904 }, "TrainerController.advance": { "total": 683.5392678530907, "count": 18211, "self": 0.47428005311121524, "children": { "env_step": { "total": 683.0649877999795, "count": 18211, "self": 540.2831138090742, "children": { "SubprocessEnvManager._take_step": { "total": 142.32900804891506, "count": 18211, "self": 2.697478199809666, "children": { "TorchPolicy.evaluate": { "total": 139.6315298491054, "count": 18211, "self": 139.6315298491054 } } }, "workers": { "total": 0.45286594199023966, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 685.089505107042, "count": 18211, "is_parallel": true, "self": 353.2331788320653, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002701184000216017, "count": 1, "is_parallel": true, "self": 0.0007869420014685602, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019142419987474568, "count": 10, "is_parallel": true, "self": 0.0019142419987474568 } } }, "UnityEnvironment.step": { "total": 0.07612469800005783, "count": 1, "is_parallel": true, "self": 0.0009638999990784214, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004944689999319962, "count": 1, "is_parallel": true, "self": 0.0004944689999319962 }, "communicator.exchange": { "total": 0.07223946200065257, "count": 1, "is_parallel": true, "self": 0.07223946200065257 }, "steps_from_proto": { "total": 0.00242686700039485, "count": 1, "is_parallel": true, "self": 0.0004909889994451078, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019358780009497423, "count": 10, "is_parallel": true, "self": 0.0019358780009497423 } } } } } } }, "UnityEnvironment.step": { "total": 331.8563262749767, "count": 18210, "is_parallel": true, "self": 16.039744162993884, "children": { "UnityEnvironment._generate_step_input": { "total": 7.922684798957562, "count": 18210, "is_parallel": true, "self": 7.922684798957562 }, "communicator.exchange": { "total": 261.850786741049, "count": 18210, "is_parallel": true, "self": 261.850786741049 }, "steps_from_proto": { "total": 46.043110571976285, "count": 18210, "is_parallel": true, "self": 9.297504443178696, "children": { "_process_rank_one_or_two_observation": { "total": 36.74560612879759, "count": 182100, "is_parallel": true, "self": 36.74560612879759 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002805759995681001, "count": 1, "self": 0.0002805759995681001, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 677.6107948141916, "count": 712972, "is_parallel": true, "self": 17.137674548855102, "children": { "process_trajectory": { "total": 360.8141546473289, "count": 712972, "is_parallel": true, "self": 359.4495456923296, "children": { "RLTrainer._checkpoint": { "total": 1.3646089549993121, "count": 4, "is_parallel": true, "self": 1.3646089549993121 } } }, "_update_policy": { "total": 299.65896561800764, "count": 90, "is_parallel": true, "self": 130.54220798797542, "children": { "TorchPPOOptimizer.update": { "total": 169.11675763003223, "count": 4587, "is_parallel": true, "self": 169.11675763003223 } } } } } } } } }, "TrainerController._save_models": { "total": 0.17218608099938137, "count": 1, "self": 0.002373593997617718, "children": { "RLTrainer._checkpoint": { "total": 0.16981248700176366, "count": 1, "self": 0.16981248700176366 } } } } } } }