{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9555771946907043, "min": 0.9531955122947693, "max": 2.729161024093628, "count": 19 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9102.828125, "min": 9102.828125, "max": 26601.55859375, "count": 19 }, "SnowballTarget.Step.mean": { "value": 199960.0, "min": 19968.0, "max": 199960.0, "count": 19 }, "SnowballTarget.Step.sum": { "value": 199960.0, "min": 19968.0, "max": 199960.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.639564514160156, "min": 1.5505114793777466, "max": 12.639564514160156, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2464.715087890625, "min": 210.86956787109375, "max": 2545.27587890625, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 6567.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06779544857358012, "min": 0.0625097456477199, "max": 0.07532066806292563, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2711817942943205, "min": 0.19933996502304047, "max": 0.37660334031462817, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20238702977989234, "min": 0.18720294447506175, "max": 0.2890216240695878, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8095481191195694, "min": 0.6170700874325692, "max": 1.3757285975358065, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.214097262000005e-06, "min": 8.214097262000005e-06, "max": 0.000273864008712, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.285638904800002e-05, "min": 3.285638904800002e-05, "max": 0.00123732008756, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10273800000000001, "min": 0.10273800000000001, "max": 0.19128799999999999, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41095200000000004, "min": 0.41095200000000004, "max": 0.9124400000000001, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001466262000000001, "min": 0.0001466262000000001, "max": 0.004565271199999999, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005865048000000004, "min": 0.0005865048000000004, "max": 0.020630756, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.522727272727273, "min": 6.636363636363637, "max": 25.522727272727273, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 219.0, "max": 1354.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 6.636363636363637, "max": 25.522727272727273, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 219.0, "max": 1354.0, "count": 19 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679087305", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679087760" }, "total": 454.47214893499995, "count": 1, "self": 0.38305882599991037, "children": { "run_training.setup": { "total": 0.18540138000003026, "count": 1, "self": 0.18540138000003026 }, "TrainerController.start_learning": { "total": 453.903688729, "count": 1, "self": 0.5803683109929807, "children": { "TrainerController._reset_env": { "total": 6.013717145999976, "count": 1, "self": 6.013717145999976 }, "TrainerController.advance": { "total": 447.18101703000707, "count": 17000, "self": 0.29113066399622767, "children": { "env_step": { "total": 446.88988636601084, "count": 17000, "self": 321.7251976679946, "children": { "SubprocessEnvManager._take_step": { "total": 124.8861289540007, "count": 17000, "self": 2.323696690005704, "children": { "TorchPolicy.evaluate": { "total": 122.56243226399499, "count": 17000, "self": 122.56243226399499 } } }, "workers": { "total": 0.2785597440155243, "count": 17000, "self": 0.0, "children": { "worker_root": { "total": 452.4741243759946, "count": 17000, "is_parallel": true, "self": 213.28853657200193, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031129779999901075, "count": 1, "is_parallel": true, "self": 0.0009860399999297442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021269380000603633, "count": 10, "is_parallel": true, "self": 0.0021269380000603633 } } }, "UnityEnvironment.step": { "total": 0.052412438000033035, "count": 1, "is_parallel": true, "self": 0.0005429159999721378, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031134900007145916, "count": 1, "is_parallel": true, "self": 0.00031134900007145916 }, "communicator.exchange": { "total": 0.04970026199998756, "count": 1, "is_parallel": true, "self": 0.04970026199998756 }, "steps_from_proto": { "total": 0.0018579110000018773, "count": 1, "is_parallel": true, "self": 0.0003948490000311722, "children": { "_process_rank_one_or_two_observation": { "total": 0.001463061999970705, "count": 10, "is_parallel": true, "self": 0.001463061999970705 } } } } } } }, "UnityEnvironment.step": { "total": 239.1855878039927, "count": 16999, "is_parallel": true, "self": 9.119688853002458, "children": { "UnityEnvironment._generate_step_input": { "total": 5.09729963199436, "count": 16999, "is_parallel": true, "self": 5.09729963199436 }, "communicator.exchange": { "total": 194.3885450259993, "count": 16999, "is_parallel": true, "self": 194.3885450259993 }, "steps_from_proto": { "total": 30.58005429299658, "count": 16999, "is_parallel": true, "self": 6.305617006002649, "children": { "_process_rank_one_or_two_observation": { "total": 24.27443728699393, "count": 169990, "is_parallel": true, "self": 24.27443728699393 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.352099997755431e-05, "count": 1, "self": 3.352099997755431e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.6191421599615, "count": 413911, "is_parallel": true, "self": 10.168503500958195, "children": { "process_trajectory": { "total": 248.3985289960027, "count": 413911, "is_parallel": true, "self": 247.65049026500287, "children": { "RLTrainer._checkpoint": { "total": 0.7480387309998378, "count": 4, "is_parallel": true, "self": 0.7480387309998378 } } }, "_update_policy": { "total": 185.05210966300058, "count": 84, "is_parallel": true, "self": 65.93473184300376, "children": { "TorchPPOOptimizer.update": { "total": 119.11737781999682, "count": 4281, "is_parallel": true, "self": 119.11737781999682 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12855272100000548, "count": 1, "self": 0.001085244000023522, "children": { "RLTrainer._checkpoint": { "total": 0.12746747699998195, "count": 1, "self": 0.12746747699998195 } } } } } } }