{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9017541408538818, "min": 0.8800185918807983, "max": 2.864156723022461, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8570.271484375, "min": 8570.271484375, "max": 29237.3125, "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": 13.08511734008789, "min": 0.3743511736392975, "max": 13.146700859069824, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2551.597900390625, "min": 72.62413024902344, "max": 2681.927001953125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.059888771427686865, "min": 0.059888771427686865, "max": 0.07652964517211669, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.23955508571074746, "min": 0.23955508571074746, "max": 0.3667346069899698, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1810429862097782, "min": 0.12499964554616086, "max": 0.31244204098395273, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7241719448391128, "min": 0.49999858218464344, "max": 1.4184734190211576, "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": 25.25, "min": 3.5, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 154.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.5, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 154.0, "max": 1401.0, "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": "1754575012", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1754575421" }, "total": 409.6682677660001, "count": 1, "self": 0.38842840800020895, "children": { "run_training.setup": { "total": 0.023620600999947783, "count": 1, "self": 0.023620600999947783 }, "TrainerController.start_learning": { "total": 409.25621875699994, "count": 1, "self": 0.3186369720167477, "children": { "TrainerController._reset_env": { "total": 3.0430786679999073, "count": 1, "self": 3.0430786679999073 }, "TrainerController.advance": { "total": 405.81555782998316, "count": 18192, "self": 0.3360236099888425, "children": { "env_step": { "total": 287.1742037230065, "count": 18192, "self": 220.94227391700088, "children": { "SubprocessEnvManager._take_step": { "total": 66.03724669800431, "count": 18192, "self": 1.153795124993394, "children": { "TorchPolicy.evaluate": { "total": 64.88345157301092, "count": 18192, "self": 64.88345157301092 } } }, "workers": { "total": 0.19468310800129984, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 407.95788041402034, "count": 18192, "is_parallel": true, "self": 213.47796034702105, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056358849999469385, "count": 1, "is_parallel": true, "self": 0.0042538319996765495, "children": { "_process_rank_one_or_two_observation": { "total": 0.001382053000270389, "count": 10, "is_parallel": true, "self": 0.001382053000270389 } } }, "UnityEnvironment.step": { "total": 0.03372978100014734, "count": 1, "is_parallel": true, "self": 0.0005554949998440861, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041522900005475094, "count": 1, "is_parallel": true, "self": 0.00041522900005475094 }, "communicator.exchange": { "total": 0.030933399000105055, "count": 1, "is_parallel": true, "self": 0.030933399000105055 }, "steps_from_proto": { "total": 0.0018256580001434486, "count": 1, "is_parallel": true, "self": 0.0003492600001209212, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014763980000225274, "count": 10, "is_parallel": true, "self": 0.0014763980000225274 } } } } } } }, "UnityEnvironment.step": { "total": 194.47992006699928, "count": 18191, "is_parallel": true, "self": 9.633462490995726, "children": { "UnityEnvironment._generate_step_input": { "total": 5.177144745989381, "count": 18191, "is_parallel": true, "self": 5.177144745989381 }, "communicator.exchange": { "total": 149.63725193001324, "count": 18191, "is_parallel": true, "self": 149.63725193001324 }, "steps_from_proto": { "total": 30.032060900000943, "count": 18191, "is_parallel": true, "self": 5.213516592987844, "children": { "_process_rank_one_or_two_observation": { "total": 24.8185443070131, "count": 181910, "is_parallel": true, "self": 24.8185443070131 } } } } } } } } } } }, "trainer_advance": { "total": 118.30533049698784, "count": 18192, "self": 0.38783474898696113, "children": { "process_trajectory": { "total": 25.882727737000778, "count": 18192, "self": 25.498253453000643, "children": { "RLTrainer._checkpoint": { "total": 0.3844742840001345, "count": 4, "self": 0.3844742840001345 } } }, "_update_policy": { "total": 92.0347680110001, "count": 90, "self": 37.87165259799622, "children": { "TorchPPOOptimizer.update": { "total": 54.16311541300388, "count": 4587, "self": 54.16311541300388 } } } } } } }, "trainer_threads": { "total": 1.2190000688860891e-06, "count": 1, "self": 1.2190000688860891e-06 }, "TrainerController._save_models": { "total": 0.07894406800005527, "count": 1, "self": 0.0007914590000837052, "children": { "RLTrainer._checkpoint": { "total": 0.07815260899997156, "count": 1, "self": 0.07815260899997156 } } } } } } }