{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0826034545898438, "min": 1.0820517539978027, "max": 2.8694424629211426, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10396.2412109375, "min": 10396.2412109375, "max": 29449.087890625, "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": 12.596543312072754, "min": 0.3283672034740448, "max": 12.596543312072754, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2456.325927734375, "min": 63.70323944091797, "max": 2532.3798828125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06316947675696058, "min": 0.06174796104567255, "max": 0.07854601014917659, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2526779070278423, "min": 0.2469918441826902, "max": 0.3436602945804742, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23242917094452709, "min": 0.11346812157174938, "max": 0.31324700794967947, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9297166837781083, "min": 0.4538724862869975, "max": 1.5662350397483973, "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": 0.001385256038248, "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": 0.961752, "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": 0.0230914248, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.522727272727273, "min": 3.227272727272727, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1079.0, "min": 142.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.522727272727273, "min": 3.227272727272727, "max": 24.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1079.0, "min": 142.0, "max": 1370.0, "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": "1776889179", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/home/hamzachera/repos/deep-rl/.venv/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": "1776889588" }, "total": 408.0754084460059, "count": 1, "self": 0.3045092000029399, "children": { "run_training.setup": { "total": 0.02482890000101179, "count": 1, "self": 0.02482890000101179 }, "TrainerController.start_learning": { "total": 407.74607034600194, "count": 1, "self": 0.47354899785568705, "children": { "TrainerController._reset_env": { "total": 2.1043681090013706, "count": 1, "self": 2.1043681090013706 }, "TrainerController.advance": { "total": 405.0646929391514, "count": 18204, "self": 0.21666630054096458, "children": { "env_step": { "total": 404.84802663861046, "count": 18204, "self": 206.1553312023534, "children": { "SubprocessEnvManager._take_step": { "total": 198.45649523701286, "count": 18204, "self": 1.3883133931158227, "children": { "TorchPolicy.evaluate": { "total": 197.06818184389704, "count": 18204, "self": 197.06818184389704 } } }, "workers": { "total": 0.23620019924419466, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 406.82365954777924, "count": 18204, "is_parallel": true, "self": 274.64467404285097, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020000999938929453, "count": 1, "is_parallel": true, "self": 0.0006420999925467186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013580000013462268, "count": 10, "is_parallel": true, "self": 0.0013580000013462268 } } }, "UnityEnvironment.step": { "total": 0.027208099993003998, "count": 1, "is_parallel": true, "self": 0.0002907999951275997, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035260000004200265, "count": 1, "is_parallel": true, "self": 0.00035260000004200265 }, "communicator.exchange": { "total": 0.025391299997863825, "count": 1, "is_parallel": true, "self": 0.025391299997863825 }, "steps_from_proto": { "total": 0.0011733999999705702, "count": 1, "is_parallel": true, "self": 0.00021649998961947858, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009569000103510916, "count": 10, "is_parallel": true, "self": 0.0009569000103510916 } } } } } } }, "UnityEnvironment.step": { "total": 132.17898550492828, "count": 18203, "is_parallel": true, "self": 4.9460476846506936, "children": { "UnityEnvironment._generate_step_input": { "total": 3.163810793463199, "count": 18203, "is_parallel": true, "self": 3.163810793463199 }, "communicator.exchange": { "total": 108.39317067309457, "count": 18203, "is_parallel": true, "self": 108.39317067309457 }, "steps_from_proto": { "total": 15.675956353719812, "count": 18203, "is_parallel": true, "self": 3.3482303901109844, "children": { "_process_rank_one_or_two_observation": { "total": 12.327725963608827, "count": 182030, "is_parallel": true, "self": 12.327725963608827 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018419999832985923, "count": 1, "self": 0.00018419999832985923, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 402.60944884323544, "count": 388217, "is_parallel": true, "self": 7.0693147873389535, "children": { "process_trajectory": { "total": 229.02327211391093, "count": 388217, "is_parallel": true, "self": 223.20147152689606, "children": { "RLTrainer._checkpoint": { "total": 5.821800587014877, "count": 40, "is_parallel": true, "self": 5.821800587014877 } } }, "_update_policy": { "total": 166.51686194198555, "count": 90, "is_parallel": true, "self": 27.427308523852844, "children": { "TorchPPOOptimizer.update": { "total": 139.0895534181327, "count": 4578, "is_parallel": true, "self": 139.0895534181327 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10327609999512788, "count": 1, "self": 0.0007502999942516908, "children": { "RLTrainer._checkpoint": { "total": 0.10252580000087619, "count": 1, "self": 0.10252580000087619 } } } } } } }