{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9459652900695801, "min": 0.9459652900695801, "max": 2.863677740097046, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9052.8876953125, "min": 9052.8876953125, "max": 29389.92578125, "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": 12.673412322998047, "min": 0.2736020088195801, "max": 12.673412322998047, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2471.3154296875, "min": 53.07878875732422, "max": 2540.0654296875, "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.Losses.PolicyLoss.mean": { "value": 0.07012406368291932, "min": 0.061339522445058386, "max": 0.07188053482298296, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2804962547316773, "min": 0.24535808978023355, "max": 0.35307358917962833, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18678169025509966, "min": 0.11659374337428816, "max": 0.27793770093543857, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7471267610203987, "min": 0.4663749734971526, "max": 1.2849259855700477, "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.CumulativeReward.mean": { "value": 25.431818181818183, "min": 3.022727272727273, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 133.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.022727272727273, "max": 25.431818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 133.0, "max": 1379.0, "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": "1721161532", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/john/miniconda3/envs/unit5/bin/mlagents-learn ../config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721161716" }, "total": 184.0504257879984, "count": 1, "self": 0.21740150100231403, "children": { "run_training.setup": { "total": 0.011563694999495056, "count": 1, "self": 0.011563694999495056 }, "TrainerController.start_learning": { "total": 183.82146059199658, "count": 1, "self": 0.19760472519919858, "children": { "TrainerController._reset_env": { "total": 0.8619703519980249, "count": 1, "self": 0.8619703519980249 }, "TrainerController.advance": { "total": 182.71300816379517, "count": 18204, "self": 0.1000716349153663, "children": { "env_step": { "total": 182.6129365288798, "count": 18204, "self": 123.64079770399258, "children": { "SubprocessEnvManager._take_step": { "total": 58.86991431299248, "count": 18204, "self": 0.5383992309616588, "children": { "TorchPolicy.evaluate": { "total": 58.33151508203082, "count": 18204, "self": 58.33151508203082 } } }, "workers": { "total": 0.10222451189474668, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 183.52980233595008, "count": 18204, "is_parallel": true, "self": 90.72314659201584, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000977309999143472, "count": 1, "is_parallel": true, "self": 0.0002817799977492541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006955300013942178, "count": 10, "is_parallel": true, "self": 0.0006955300013942178 } } }, "UnityEnvironment.step": { "total": 0.01426788700337056, "count": 1, "is_parallel": true, "self": 0.00018270100190420635, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016143000175361522, "count": 1, "is_parallel": true, "self": 0.00016143000175361522 }, "communicator.exchange": { "total": 0.01334110500101815, "count": 1, "is_parallel": true, "self": 0.01334110500101815 }, "steps_from_proto": { "total": 0.0005826509986945894, "count": 1, "is_parallel": true, "self": 0.00013158999718143605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004510610015131533, "count": 10, "is_parallel": true, "self": 0.0004510610015131533 } } } } } } }, "UnityEnvironment.step": { "total": 92.80665574393424, "count": 18203, "is_parallel": true, "self": 4.022721519802872, "children": { "UnityEnvironment._generate_step_input": { "total": 1.9994408670863777, "count": 18203, "is_parallel": true, "self": 1.9994408670863777 }, "communicator.exchange": { "total": 74.80697977204181, "count": 18203, "is_parallel": true, "self": 74.80697977204181 }, "steps_from_proto": { "total": 11.97751358500318, "count": 18203, "is_parallel": true, "self": 2.153920377317263, "children": { "_process_rank_one_or_two_observation": { "total": 9.823593207685917, "count": 182030, "is_parallel": true, "self": 9.823593207685917 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.372000229428522e-05, "count": 1, "self": 8.372000229428522e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 182.09657914328272, "count": 270558, "is_parallel": true, "self": 1.8896819435831276, "children": { "process_trajectory": { "total": 100.15845836069639, "count": 270558, "is_parallel": true, "self": 99.82853184669511, "children": { "RLTrainer._checkpoint": { "total": 0.32992651400127215, "count": 4, "is_parallel": true, "self": 0.32992651400127215 } } }, "_update_policy": { "total": 80.04843883900321, "count": 90, "is_parallel": true, "self": 19.110456332746253, "children": { "TorchPPOOptimizer.update": { "total": 60.93798250625696, "count": 4587, "is_parallel": true, "self": 60.93798250625696 } } } } } } } } }, "TrainerController._save_models": { "total": 0.048793631001899485, "count": 1, "self": 0.0009603110011084937, "children": { "RLTrainer._checkpoint": { "total": 0.04783332000079099, "count": 1, "self": 0.04783332000079099 } } } } } } }