{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7051005959510803, "min": 0.7031011581420898, "max": 2.862201690673828, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7158.88623046875, "min": 6790.55078125, "max": 29532.197265625, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.540824890136719, "min": 0.35199105739593506, "max": 13.561790466308594, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2640.4609375, "min": 68.28626251220703, "max": 2780.1669921875, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06690554917012753, "min": 0.06088974203117757, "max": 0.07555335789505739, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2676221966805101, "min": 0.25626725806653794, "max": 0.37144413653361114, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19295535842869796, "min": 0.13255297954139464, "max": 0.27097845048296687, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7718214337147918, "min": 0.5302119181655786, "max": 1.3548922524148344, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.891098702999994e-06, "min": 3.891098702999994e-06, "max": 0.000295941001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5564394811999976e-05, "min": 1.5564394811999976e-05, "max": 0.0014425800191399996, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101297, "min": 0.101297, "max": 0.19864700000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405188, "min": 0.405188, "max": 0.98086, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999992e-05, "min": 7.472029999999992e-05, "max": 0.004932485299999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999966, "min": 0.00029888119999999966, "max": 0.024044914, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.636363636363637, "min": 3.477272727272727, "max": 26.954545454545453, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1172.0, "min": 153.0, "max": 1473.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.636363636363637, "min": 3.477272727272727, "max": 26.954545454545453, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1172.0, "min": 153.0, "max": 1473.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725453952", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725454944" }, "total": 991.4360582860002, "count": 1, "self": 0.8433071760002804, "children": { "run_training.setup": { "total": 0.09433208999985254, "count": 1, "self": 0.09433208999985254 }, "TrainerController.start_learning": { "total": 990.49841902, "count": 1, "self": 1.404796138976053, "children": { "TrainerController._reset_env": { "total": 2.063632901000119, "count": 1, "self": 2.063632901000119 }, "TrainerController.advance": { "total": 986.8909946010235, "count": 36400, "self": 0.666640316047733, "children": { "env_step": { "total": 986.2243542849758, "count": 36400, "self": 762.5765003389361, "children": { "SubprocessEnvManager._take_step": { "total": 222.96883892899564, "count": 36400, "self": 3.2384945550181783, "children": { "TorchPolicy.evaluate": { "total": 219.73034437397746, "count": 36400, "self": 219.73034437397746 } } }, "workers": { "total": 0.6790150170440938, "count": 36400, "self": 0.0, "children": { "worker_root": { "total": 987.6894136619951, "count": 36400, "is_parallel": true, "self": 465.6858180239751, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034341000000495114, "count": 1, "is_parallel": true, "self": 0.0009449889992083627, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024891110008411488, "count": 10, "is_parallel": true, "self": 0.0024891110008411488 } } }, "UnityEnvironment.step": { "total": 0.041506202999926245, "count": 1, "is_parallel": true, "self": 0.0007951229997615883, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000439310000047044, "count": 1, "is_parallel": true, "self": 0.000439310000047044 }, "communicator.exchange": { "total": 0.03784137100001317, "count": 1, "is_parallel": true, "self": 0.03784137100001317 }, "steps_from_proto": { "total": 0.002430399000104444, "count": 1, "is_parallel": true, "self": 0.0004391139998460858, "children": { "_process_rank_one_or_two_observation": { "total": 0.001991285000258358, "count": 10, "is_parallel": true, "self": 0.001991285000258358 } } } } } } }, "UnityEnvironment.step": { "total": 522.00359563802, "count": 36399, "is_parallel": true, "self": 23.61631140800364, "children": { "UnityEnvironment._generate_step_input": { "total": 12.593769466023787, "count": 36399, "is_parallel": true, "self": 12.593769466023787 }, "communicator.exchange": { "total": 407.76271768503784, "count": 36399, "is_parallel": true, "self": 407.76271768503784 }, "steps_from_proto": { "total": 78.03079707895472, "count": 36399, "is_parallel": true, "self": 15.079791963075877, "children": { "_process_rank_one_or_two_observation": { "total": 62.95100511587884, "count": 363990, "is_parallel": true, "self": 62.95100511587884 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003482560000520607, "count": 1, "self": 0.0003482560000520607, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 975.9914055799559, "count": 1260681, "is_parallel": true, "self": 27.35761915393823, "children": { "process_trajectory": { "total": 517.4998755560196, "count": 1260681, "is_parallel": true, "self": 515.6441714610194, "children": { "RLTrainer._checkpoint": { "total": 1.855704095000192, "count": 8, "is_parallel": true, "self": 1.855704095000192 } } }, "_update_policy": { "total": 431.1339108699981, "count": 181, "is_parallel": true, "self": 129.55837340199787, "children": { "TorchPPOOptimizer.update": { "total": 301.5755374680002, "count": 9228, "is_parallel": true, "self": 301.5755374680002 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1386471230002826, "count": 1, "self": 0.002383123000527121, "children": { "RLTrainer._checkpoint": { "total": 0.13626399999975547, "count": 1, "self": 0.13626399999975547 } } } } } } }