{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8662530779838562, "min": 0.8662530779838562, "max": 2.861605644226074, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8232.869140625, "min": 8232.869140625, "max": 29211.271484375, "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": 12.90109920501709, "min": 0.4649038314819336, "max": 12.90109920501709, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.71435546875, "min": 90.19134521484375, "max": 2598.2861328125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06523991378515562, "min": 0.06285916178737407, "max": 0.07534599267799459, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26095965514062247, "min": 0.25143664714949626, "max": 0.37672996338997294, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20340968018361166, "min": 0.12052021835766294, "max": 0.2910125501746056, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8136387207344467, "min": 0.48208087343065176, "max": 1.3805400144820121, "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": 25.431818181818183, "min": 3.25, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 143.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.25, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 143.0, "max": 1405.0, "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": "1754266421", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/envs/myenv/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754266789" }, "total": 367.56691434100003, "count": 1, "self": 0.3210412109999652, "children": { "run_training.setup": { "total": 0.017988106000075277, "count": 1, "self": 0.017988106000075277 }, "TrainerController.start_learning": { "total": 367.227885024, "count": 1, "self": 0.30235131500808166, "children": { "TrainerController._reset_env": { "total": 2.1785497629998645, "count": 1, "self": 2.1785497629998645 }, "TrainerController.advance": { "total": 364.667632422992, "count": 18192, "self": 0.30975940202529273, "children": { "env_step": { "total": 252.19770677098722, "count": 18192, "self": 188.16066464798314, "children": { "SubprocessEnvManager._take_step": { "total": 63.849439101006965, "count": 18192, "self": 1.11950220400513, "children": { "TorchPolicy.evaluate": { "total": 62.729936897001835, "count": 18192, "self": 62.729936897001835 } } }, "workers": { "total": 0.18760302199711987, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 366.4366161509947, "count": 18192, "is_parallel": true, "self": 200.3564121299646, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020728759998291935, "count": 1, "is_parallel": true, "self": 0.0006149849994017131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014578910004274803, "count": 10, "is_parallel": true, "self": 0.0014578910004274803 } } }, "UnityEnvironment.step": { "total": 0.03226952399995753, "count": 1, "is_parallel": true, "self": 0.0006007239996961289, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003017670001099759, "count": 1, "is_parallel": true, "self": 0.0003017670001099759 }, "communicator.exchange": { "total": 0.02935412300007556, "count": 1, "is_parallel": true, "self": 0.02935412300007556 }, "steps_from_proto": { "total": 0.0020129100000758626, "count": 1, "is_parallel": true, "self": 0.00038402700010919943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016288829999666632, "count": 10, "is_parallel": true, "self": 0.0016288829999666632 } } } } } } }, "UnityEnvironment.step": { "total": 166.0802040210301, "count": 18191, "is_parallel": true, "self": 5.915615151994416, "children": { "UnityEnvironment._generate_step_input": { "total": 3.2124131350160496, "count": 18191, "is_parallel": true, "self": 3.2124131350160496 }, "communicator.exchange": { "total": 138.16316751001796, "count": 18191, "is_parallel": true, "self": 138.16316751001796 }, "steps_from_proto": { "total": 18.78900822400169, "count": 18191, "is_parallel": true, "self": 3.5464636529443396, "children": { "_process_rank_one_or_two_observation": { "total": 15.242544571057351, "count": 181910, "is_parallel": true, "self": 15.242544571057351 } } } } } } } } } } }, "trainer_advance": { "total": 112.16016624997951, "count": 18192, "self": 0.36195818697501636, "children": { "process_trajectory": { "total": 24.51708807700379, "count": 18192, "self": 24.152739596003585, "children": { "RLTrainer._checkpoint": { "total": 0.36434848100020645, "count": 4, "self": 0.36434848100020645 } } }, "_update_policy": { "total": 87.2811199860007, "count": 90, "self": 35.451537635011846, "children": { "TorchPPOOptimizer.update": { "total": 51.82958235098886, "count": 4587, "self": 51.82958235098886 } } } } } } }, "trainer_threads": { "total": 1.0369999472459313e-06, "count": 1, "self": 1.0369999472459313e-06 }, "TrainerController._save_models": { "total": 0.07935048600006667, "count": 1, "self": 0.0007994270001745463, "children": { "RLTrainer._checkpoint": { "total": 0.07855105899989212, "count": 1, "self": 0.07855105899989212 } } } } } } }