{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8420787453651428, "min": 0.8420787453651428, "max": 2.8625736236572266, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8003.1162109375, "min": 8003.1162109375, "max": 29221.15234375, "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": 13.228395462036133, "min": 0.5035557150840759, "max": 13.228395462036133, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2579.537109375, "min": 97.68980407714844, "max": 2695.68212890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06904638772710528, "min": 0.06166020506894783, "max": 0.07373721250926382, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2761855509084211, "min": 0.25503849752610275, "max": 0.3686860625463191, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20142870871167556, "min": 0.14005450415425003, "max": 0.28048249564918815, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8057148348467023, "min": 0.5602180166170001, "max": 1.4024124782459408, "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": 26.09090909090909, "min": 3.977272727272727, "max": 26.472727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1148.0, "min": 175.0, "max": 1456.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.09090909090909, "min": 3.977272727272727, "max": 26.472727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1148.0, "min": 175.0, "max": 1456.0, "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": "1741745573", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741746060" }, "total": 486.859215643, "count": 1, "self": 0.43948498799994695, "children": { "run_training.setup": { "total": 0.0404594100000395, "count": 1, "self": 0.0404594100000395 }, "TrainerController.start_learning": { "total": 486.37927124500004, "count": 1, "self": 0.41491404799393194, "children": { "TrainerController._reset_env": { "total": 3.8309041170000455, "count": 1, "self": 3.8309041170000455 }, "TrainerController.advance": { "total": 482.03084730400604, "count": 18192, "self": 0.47085410800542604, "children": { "env_step": { "total": 345.7108646989975, "count": 18192, "self": 261.47123622300495, "children": { "SubprocessEnvManager._take_step": { "total": 83.98766351599568, "count": 18192, "self": 1.473245178999946, "children": { "TorchPolicy.evaluate": { "total": 82.51441833699573, "count": 18192, "self": 82.51441833699573 } } }, "workers": { "total": 0.25196495999688295, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 484.6442554669926, "count": 18192, "is_parallel": true, "self": 255.88279191199695, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0077747810000232676, "count": 1, "is_parallel": true, "self": 0.005096027000035974, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026787539999872934, "count": 10, "is_parallel": true, "self": 0.0026787539999872934 } } }, "UnityEnvironment.step": { "total": 0.04313565400002517, "count": 1, "is_parallel": true, "self": 0.0007152120000455398, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046134999996638726, "count": 1, "is_parallel": true, "self": 0.00046134999996638726 }, "communicator.exchange": { "total": 0.039550735000034365, "count": 1, "is_parallel": true, "self": 0.039550735000034365 }, "steps_from_proto": { "total": 0.002408356999978878, "count": 1, "is_parallel": true, "self": 0.00045056399989107376, "children": { "_process_rank_one_or_two_observation": { "total": 0.001957793000087804, "count": 10, "is_parallel": true, "self": 0.001957793000087804 } } } } } } }, "UnityEnvironment.step": { "total": 228.76146355499566, "count": 18191, "is_parallel": true, "self": 11.064770819001865, "children": { "UnityEnvironment._generate_step_input": { "total": 6.291202456993233, "count": 18191, "is_parallel": true, "self": 6.291202456993233 }, "communicator.exchange": { "total": 174.82710657799515, "count": 18191, "is_parallel": true, "self": 174.82710657799515 }, "steps_from_proto": { "total": 36.57838370100541, "count": 18191, "is_parallel": true, "self": 6.7102560469925265, "children": { "_process_rank_one_or_two_observation": { "total": 29.86812765401288, "count": 181910, "is_parallel": true, "self": 29.86812765401288 } } } } } } } } } } }, "trainer_advance": { "total": 135.8491284970031, "count": 18192, "self": 0.5000056670073718, "children": { "process_trajectory": { "total": 30.252582493994623, "count": 18192, "self": 29.529683940994573, "children": { "RLTrainer._checkpoint": { "total": 0.72289855300005, "count": 4, "self": 0.72289855300005 } } }, "_update_policy": { "total": 105.09654033600111, "count": 90, "self": 42.291469808000556, "children": { "TorchPPOOptimizer.update": { "total": 62.805070528000556, "count": 4587, "self": 62.805070528000556 } } } } } } }, "trainer_threads": { "total": 1.2210000477352878e-06, "count": 1, "self": 1.2210000477352878e-06 }, "TrainerController._save_models": { "total": 0.10260455499997079, "count": 1, "self": 0.0009255879999727767, "children": { "RLTrainer._checkpoint": { "total": 0.10167896699999801, "count": 1, "self": 0.10167896699999801 } } } } } } }