{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8882440328598022, "min": 0.8816142082214355, "max": 2.8713157176971436, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8480.9541015625, "min": 8480.9541015625, "max": 29373.55859375, "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": 12.986055374145508, "min": 0.275983989238739, "max": 12.986055374145508, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2532.28076171875, "min": 53.5408935546875, "max": 2608.881591796875, "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": 0.06671183112092538, "min": 0.06415494712875407, "max": 0.07795732948899396, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2668473244837015, "min": 0.2605476464891313, "max": 0.3897866474449698, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1962445849077959, "min": 0.10253968159896412, "max": 0.29239631648741515, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7849783396311836, "min": 0.4101587263958565, "max": 1.4251060798472048, "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": 25.977272727272727, "min": 2.659090909090909, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 117.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 2.659090909090909, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 117.0, "max": 1392.0, "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": "1708932162", "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=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708932640" }, "total": 478.05793344999984, "count": 1, "self": 0.42557674899967424, "children": { "run_training.setup": { "total": 0.06160459000011542, "count": 1, "self": 0.06160459000011542 }, "TrainerController.start_learning": { "total": 477.57075211100005, "count": 1, "self": 0.64167830801739, "children": { "TrainerController._reset_env": { "total": 3.6737769190001472, "count": 1, "self": 3.6737769190001472 }, "TrainerController.advance": { "total": 473.1598187809825, "count": 18199, "self": 0.2872777350137312, "children": { "env_step": { "total": 472.8725410459688, "count": 18199, "self": 306.0788504279992, "children": { "SubprocessEnvManager._take_step": { "total": 166.47259133198327, "count": 18199, "self": 1.6101152429500871, "children": { "TorchPolicy.evaluate": { "total": 164.86247608903318, "count": 18199, "self": 164.86247608903318 } } }, "workers": { "total": 0.32109928598629267, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 476.3138893839953, "count": 18199, "is_parallel": true, "self": 235.3901449649843, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007154947000117318, "count": 1, "is_parallel": true, "self": 0.004664585000227817, "children": { "_process_rank_one_or_two_observation": { "total": 0.002490361999889501, "count": 10, "is_parallel": true, "self": 0.002490361999889501 } } }, "UnityEnvironment.step": { "total": 0.042447708999816314, "count": 1, "is_parallel": true, "self": 0.0007448349999776838, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043620799988275394, "count": 1, "is_parallel": true, "self": 0.00043620799988275394 }, "communicator.exchange": { "total": 0.039179399999966336, "count": 1, "is_parallel": true, "self": 0.039179399999966336 }, "steps_from_proto": { "total": 0.0020872659999895404, "count": 1, "is_parallel": true, "self": 0.0004312539999773435, "children": { "_process_rank_one_or_two_observation": { "total": 0.001656012000012197, "count": 10, "is_parallel": true, "self": 0.001656012000012197 } } } } } } }, "UnityEnvironment.step": { "total": 240.92374441901097, "count": 18198, "is_parallel": true, "self": 11.38989289502888, "children": { "UnityEnvironment._generate_step_input": { "total": 5.9822368689910945, "count": 18198, "is_parallel": true, "self": 5.9822368689910945 }, "communicator.exchange": { "total": 185.8460481199645, "count": 18198, "is_parallel": true, "self": 185.8460481199645 }, "steps_from_proto": { "total": 37.70556653502649, "count": 18198, "is_parallel": true, "self": 6.999523547057379, "children": { "_process_rank_one_or_two_observation": { "total": 30.706042987969113, "count": 181980, "is_parallel": true, "self": 30.706042987969113 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021225999989837874, "count": 1, "self": 0.00021225999989837874, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 466.733107323033, "count": 700337, "is_parallel": true, "self": 16.275835752238436, "children": { "process_trajectory": { "total": 258.17697568979634, "count": 700337, "is_parallel": true, "self": 257.664288770796, "children": { "RLTrainer._checkpoint": { "total": 0.5126869190003163, "count": 4, "is_parallel": true, "self": 0.5126869190003163 } } }, "_update_policy": { "total": 192.2802958809982, "count": 90, "is_parallel": true, "self": 54.31668421499876, "children": { "TorchPPOOptimizer.update": { "total": 137.96361166599945, "count": 4584, "is_parallel": true, "self": 137.96361166599945 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09526584300010654, "count": 1, "self": 0.0009814370000640338, "children": { "RLTrainer._checkpoint": { "total": 0.09428440600004251, "count": 1, "self": 0.09428440600004251 } } } } } } }