{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7533261179924011, "min": 0.7533261179924011, "max": 2.8324434757232666, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7159.611328125, "min": 7159.611328125, "max": 28913.58203125, "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": 12.610748291015625, "min": 0.35638895630836487, "max": 12.610748291015625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2459.095947265625, "min": 69.13945770263672, "max": 2564.39111328125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07334922144903377, "min": 0.06357128551031102, "max": 0.0762989513916146, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2933968857961351, "min": 0.2542851420412441, "max": 0.3592074026442681, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2039990022632421, "min": 0.13703101230374373, "max": 0.2833896319509721, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8159960090529684, "min": 0.5481240492149749, "max": 1.383848043049083, "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": 24.977272727272727, "min": 3.6363636363636362, "max": 25.054545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 160.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.6363636363636362, "max": 25.054545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 160.0, "max": 1378.0, "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": "1758100185", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/server/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1758100339" }, "total": 154.42341564300295, "count": 1, "self": 0.16618596599437296, "children": { "run_training.setup": { "total": 0.017503306007711217, "count": 1, "self": 0.017503306007711217 }, "TrainerController.start_learning": { "total": 154.23972637100087, "count": 1, "self": 0.18325162251130678, "children": { "TrainerController._reset_env": { "total": 0.8397780069935834, "count": 1, "self": 0.8397780069935834 }, "TrainerController.advance": { "total": 153.1903344785096, "count": 18192, "self": 0.1579810293915216, "children": { "env_step": { "total": 110.187647107261, "count": 18192, "self": 80.45757666052668, "children": { "SubprocessEnvManager._take_step": { "total": 29.610977172094863, "count": 18192, "self": 0.5440506693266798, "children": { "TorchPolicy.evaluate": { "total": 29.066926502768183, "count": 18192, "self": 29.066926502768183 } } }, "workers": { "total": 0.11909327463945374, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 153.93816260059248, "count": 18192, "is_parallel": true, "self": 84.17524376416986, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000937588993110694, "count": 1, "is_parallel": true, "self": 0.0002483360149199143, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006892529781907797, "count": 10, "is_parallel": true, "self": 0.0006892529781907797 } } }, "UnityEnvironment.step": { "total": 0.010522388009121642, "count": 1, "is_parallel": true, "self": 0.00013782498717773706, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00012080100714229047, "count": 1, "is_parallel": true, "self": 0.00012080100714229047 }, "communicator.exchange": { "total": 0.009865151005215012, "count": 1, "is_parallel": true, "self": 0.009865151005215012 }, "steps_from_proto": { "total": 0.00039861100958660245, "count": 1, "is_parallel": true, "self": 8.964701555669308e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00030896399402990937, "count": 10, "is_parallel": true, "self": 0.00030896399402990937 } } } } } } }, "UnityEnvironment.step": { "total": 69.76291883642261, "count": 18191, "is_parallel": true, "self": 2.613528732195846, "children": { "UnityEnvironment._generate_step_input": { "total": 1.4190875760978088, "count": 18191, "is_parallel": true, "self": 1.4190875760978088 }, "communicator.exchange": { "total": 57.528806076414185, "count": 18191, "is_parallel": true, "self": 57.528806076414185 }, "steps_from_proto": { "total": 8.201496451714775, "count": 18191, "is_parallel": true, "self": 1.7491688610316487, "children": { "_process_rank_one_or_two_observation": { "total": 6.452327590683126, "count": 181910, "is_parallel": true, "self": 6.452327590683126 } } } } } } } } } } }, "trainer_advance": { "total": 42.84470634185709, "count": 18192, "self": 0.2395377919310704, "children": { "process_trajectory": { "total": 9.870848307968117, "count": 18192, "self": 9.742462730966508, "children": { "RLTrainer._checkpoint": { "total": 0.1283855770016089, "count": 4, "self": 0.1283855770016089 } } }, "_update_policy": { "total": 32.7343202419579, "count": 90, "self": 13.40410240588244, "children": { "TorchPPOOptimizer.update": { "total": 19.330217836075462, "count": 4587, "self": 19.330217836075462 } } } } } } }, "trainer_threads": { "total": 4.289904609322548e-07, "count": 1, "self": 4.289904609322548e-07 }, "TrainerController._save_models": { "total": 0.026361833995906636, "count": 1, "self": 0.0003449669893598184, "children": { "RLTrainer._checkpoint": { "total": 0.026016867006546818, "count": 1, "self": 0.026016867006546818 } } } } } } }