{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8896536827087402, "min": 0.8896536827087402, "max": 2.837280750274658, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8455.2685546875, "min": 8455.2685546875, "max": 28962.962890625, "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": 12.668874740600586, "min": 0.42954954504966736, "max": 12.668874740600586, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2470.4306640625, "min": 83.33261108398438, "max": 2547.630859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07269506207008888, "min": 0.06038849860108124, "max": 0.07444792933643375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29078024828035554, "min": 0.24155399440432496, "max": 0.3552686488141726, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2055271893155341, "min": 0.1071374223741027, "max": 0.2745663457203145, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8221087572621364, "min": 0.4285496894964108, "max": 1.3182429013883366, "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": 25.227272727272727, "min": 3.727272727272727, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 164.0, "max": 1371.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.727272727272727, "max": 25.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 164.0, "max": 1371.0, "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": "1739954772", "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=SnowballTarget2 --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": "1739955197" }, "total": 425.550319706, "count": 1, "self": 0.4363853099999915, "children": { "run_training.setup": { "total": 0.02108690799991564, "count": 1, "self": 0.02108690799991564 }, "TrainerController.start_learning": { "total": 425.0928474880001, "count": 1, "self": 0.3357555159926733, "children": { "TrainerController._reset_env": { "total": 1.8776872429999685, "count": 1, "self": 1.8776872429999685 }, "TrainerController.advance": { "total": 422.7830831670075, "count": 18192, "self": 0.3605927080411675, "children": { "env_step": { "total": 301.74031344997195, "count": 18192, "self": 229.74915283194855, "children": { "SubprocessEnvManager._take_step": { "total": 71.78745030100663, "count": 18192, "self": 1.2553487679872433, "children": { "TorchPolicy.evaluate": { "total": 70.53210153301939, "count": 18192, "self": 70.53210153301939 } } }, "workers": { "total": 0.20371031701677111, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 423.6132366119815, "count": 18192, "is_parallel": true, "self": 221.7291352489858, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022144260000231952, "count": 1, "is_parallel": true, "self": 0.000714268999900014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015001570001231812, "count": 10, "is_parallel": true, "self": 0.0015001570001231812 } } }, "UnityEnvironment.step": { "total": 0.034799811999960184, "count": 1, "is_parallel": true, "self": 0.0005477759999621412, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039800299998660194, "count": 1, "is_parallel": true, "self": 0.00039800299998660194 }, "communicator.exchange": { "total": 0.03203343600000608, "count": 1, "is_parallel": true, "self": 0.03203343600000608 }, "steps_from_proto": { "total": 0.001820597000005364, "count": 1, "is_parallel": true, "self": 0.00035336900009497185, "children": { "_process_rank_one_or_two_observation": { "total": 0.001467227999910392, "count": 10, "is_parallel": true, "self": 0.001467227999910392 } } } } } } }, "UnityEnvironment.step": { "total": 201.8841013629957, "count": 18191, "is_parallel": true, "self": 9.683065823016477, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4542930199758075, "count": 18191, "is_parallel": true, "self": 5.4542930199758075 }, "communicator.exchange": { "total": 154.78356716899805, "count": 18191, "is_parallel": true, "self": 154.78356716899805 }, "steps_from_proto": { "total": 31.96317535100536, "count": 18191, "is_parallel": true, "self": 5.6529204469694605, "children": { "_process_rank_one_or_two_observation": { "total": 26.3102549040359, "count": 181910, "is_parallel": true, "self": 26.3102549040359 } } } } } } } } } } }, "trainer_advance": { "total": 120.68217700899436, "count": 18192, "self": 0.3969057650094783, "children": { "process_trajectory": { "total": 26.627882583984388, "count": 18192, "self": 26.059318939984564, "children": { "RLTrainer._checkpoint": { "total": 0.5685636439998234, "count": 4, "self": 0.5685636439998234 } } }, "_update_policy": { "total": 93.65738866000049, "count": 90, "self": 37.39754666901365, "children": { "TorchPPOOptimizer.update": { "total": 56.25984199098684, "count": 4587, "self": 56.25984199098684 } } } } } } }, "trainer_threads": { "total": 1.0450000900164014e-06, "count": 1, "self": 1.0450000900164014e-06 }, "TrainerController._save_models": { "total": 0.09632051699986732, "count": 1, "self": 0.0009729529999731312, "children": { "RLTrainer._checkpoint": { "total": 0.09534756399989419, "count": 1, "self": 0.09534756399989419 } } } } } } }