{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9598696827888489, "min": 0.9589264392852783, "max": 2.8690896034240723, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9175.39453125, "min": 9175.39453125, "max": 29477.02734375, "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": 12.885994911193848, "min": 0.36965662240982056, "max": 12.885994911193848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2512.76904296875, "min": 71.71338653564453, "max": 2610.55908203125, "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": 0.06662445055040092, "min": 0.06420235198304142, "max": 0.0740675562524748, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2664978022016037, "min": 0.25680940793216567, "max": 0.35943714793949555, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2173380905068388, "min": 0.11093633299049757, "max": 0.29250630677915085, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8693523620273552, "min": 0.4437453319619903, "max": 1.3832480559746425, "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": 25.272727272727273, "min": 3.2045454545454546, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 141.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.2045454545454546, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 141.0, "max": 1402.0, "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": "1682483174", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1682483634" }, "total": 460.92290267500005, "count": 1, "self": 0.43391364300009627, "children": { "run_training.setup": { "total": 0.11188070599996536, "count": 1, "self": 0.11188070599996536 }, "TrainerController.start_learning": { "total": 460.377108326, "count": 1, "self": 0.5665779900041343, "children": { "TrainerController._reset_env": { "total": 3.9367556499998955, "count": 1, "self": 3.9367556499998955 }, "TrainerController.advance": { "total": 455.73660063799605, "count": 18201, "self": 0.28348402898586755, "children": { "env_step": { "total": 455.4531166090102, "count": 18201, "self": 334.6076941920146, "children": { "SubprocessEnvManager._take_step": { "total": 120.56268979799268, "count": 18201, "self": 1.7927276939954027, "children": { "TorchPolicy.evaluate": { "total": 118.76996210399727, "count": 18201, "self": 118.76996210399727 } } }, "workers": { "total": 0.2827326190028998, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 458.74429469000313, "count": 18201, "is_parallel": true, "self": 211.73078851700143, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005332208000027094, "count": 1, "is_parallel": true, "self": 0.003951002000007975, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013812060000191195, "count": 10, "is_parallel": true, "self": 0.0013812060000191195 } } }, "UnityEnvironment.step": { "total": 0.035669959000074414, "count": 1, "is_parallel": true, "self": 0.0005806110000321496, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004163820000258056, "count": 1, "is_parallel": true, "self": 0.0004163820000258056 }, "communicator.exchange": { "total": 0.032831125000029715, "count": 1, "is_parallel": true, "self": 0.032831125000029715 }, "steps_from_proto": { "total": 0.0018418409999867436, "count": 1, "is_parallel": true, "self": 0.0003810970000586167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014607439999281269, "count": 10, "is_parallel": true, "self": 0.0014607439999281269 } } } } } } }, "UnityEnvironment.step": { "total": 247.0135061730017, "count": 18200, "is_parallel": true, "self": 9.891315878008072, "children": { "UnityEnvironment._generate_step_input": { "total": 5.454665999975646, "count": 18200, "is_parallel": true, "self": 5.454665999975646 }, "communicator.exchange": { "total": 199.9050802220163, "count": 18200, "is_parallel": true, "self": 199.9050802220163 }, "steps_from_proto": { "total": 31.76244407300169, "count": 18200, "is_parallel": true, "self": 6.430840619973424, "children": { "_process_rank_one_or_two_observation": { "total": 25.331603453028265, "count": 182000, "is_parallel": true, "self": 25.331603453028265 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011034199997084215, "count": 1, "self": 0.00011034199997084215, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.1344387720094, "count": 424923, "is_parallel": true, "self": 10.311414938063422, "children": { "process_trajectory": { "total": 250.95430237194648, "count": 424923, "is_parallel": true, "self": 249.93228795594655, "children": { "RLTrainer._checkpoint": { "total": 1.0220144159999336, "count": 4, "is_parallel": true, "self": 1.0220144159999336 } } }, "_update_policy": { "total": 190.86872146199948, "count": 90, "is_parallel": true, "self": 72.87175649000096, "children": { "TorchPPOOptimizer.update": { "total": 117.99696497199852, "count": 4587, "is_parallel": true, "self": 117.99696497199852 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13706370599993534, "count": 1, "self": 0.000846744000000399, "children": { "RLTrainer._checkpoint": { "total": 0.13621696199993494, "count": 1, "self": 0.13621696199993494 } } } } } } }