{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9830034375190735, "min": 0.9830034375190735, "max": 2.8677070140838623, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9385.716796875, "min": 9385.716796875, "max": 29368.1875, "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": 12.922595977783203, "min": 0.33154726028442383, "max": 12.922595977783203, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.90625, "min": 64.3201675415039, "max": 2595.04931640625, "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": 0.06568142568864335, "min": 0.06239515137035506, "max": 0.07747008372989869, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2627257027545734, "min": 0.24958060548142025, "max": 0.36074242169977916, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19774128492994636, "min": 0.10972408506923409, "max": 0.28031995461559767, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7909651397197854, "min": 0.43889634027693636, "max": 1.375172557491882, "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": 26.0, "min": 3.2954545454545454, "max": 26.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1144.0, "min": 145.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.0, "min": 3.2954545454545454, "max": 26.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1144.0, "min": 145.0, "max": 1412.0, "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": "1691315580", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691316069" }, "total": 489.7965260149999, "count": 1, "self": 0.43220695599995906, "children": { "run_training.setup": { "total": 0.0452278859999069, "count": 1, "self": 0.0452278859999069 }, "TrainerController.start_learning": { "total": 489.31909117300006, "count": 1, "self": 0.5858932999911985, "children": { "TrainerController._reset_env": { "total": 6.59936089100006, "count": 1, "self": 6.59936089100006 }, "TrainerController.advance": { "total": 481.9876398190087, "count": 18201, "self": 0.28678374600178813, "children": { "env_step": { "total": 481.7008560730069, "count": 18201, "self": 350.3287238939922, "children": { "SubprocessEnvManager._take_step": { "total": 131.08366251700056, "count": 18201, "self": 1.768899703994748, "children": { "TorchPolicy.evaluate": { "total": 129.3147628130058, "count": 18201, "self": 129.3147628130058 } } }, "workers": { "total": 0.2884696620141085, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 487.66435661701644, "count": 18201, "is_parallel": true, "self": 229.41883246102645, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00585282500003359, "count": 1, "is_parallel": true, "self": 0.004417499000055614, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014353259999779766, "count": 10, "is_parallel": true, "self": 0.0014353259999779766 } } }, "UnityEnvironment.step": { "total": 0.07676244499998575, "count": 1, "is_parallel": true, "self": 0.007714782999869385, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004047820000323554, "count": 1, "is_parallel": true, "self": 0.0004047820000323554 }, "communicator.exchange": { "total": 0.06631129499999133, "count": 1, "is_parallel": true, "self": 0.06631129499999133 }, "steps_from_proto": { "total": 0.002331585000092673, "count": 1, "is_parallel": true, "self": 0.0003948440000840492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019367410000086238, "count": 10, "is_parallel": true, "self": 0.0019367410000086238 } } } } } } }, "UnityEnvironment.step": { "total": 258.24552415599, "count": 18200, "is_parallel": true, "self": 10.6990307759811, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4197922429985965, "count": 18200, "is_parallel": true, "self": 5.4197922429985965 }, "communicator.exchange": { "total": 204.8458746410089, "count": 18200, "is_parallel": true, "self": 204.8458746410089 }, "steps_from_proto": { "total": 37.280826496001396, "count": 18200, "is_parallel": true, "self": 6.79044210398024, "children": { "_process_rank_one_or_two_observation": { "total": 30.490384392021156, "count": 182000, "is_parallel": true, "self": 30.490384392021156 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001501930000813445, "count": 1, "self": 0.0001501930000813445, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 478.21432517496874, "count": 444171, "is_parallel": true, "self": 10.427711935966158, "children": { "process_trajectory": { "total": 261.66458366000245, "count": 444171, "is_parallel": true, "self": 260.29304357700244, "children": { "RLTrainer._checkpoint": { "total": 1.3715400830000135, "count": 4, "is_parallel": true, "self": 1.3715400830000135 } } }, "_update_policy": { "total": 206.12202957900013, "count": 90, "is_parallel": true, "self": 80.53741765899986, "children": { "TorchPPOOptimizer.update": { "total": 125.58461192000027, "count": 4584, "is_parallel": true, "self": 125.58461192000027 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14604697000004307, "count": 1, "self": 0.0009444249999432941, "children": { "RLTrainer._checkpoint": { "total": 0.14510254500009978, "count": 1, "self": 0.14510254500009978 } } } } } } }