{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.862246572971344, "min": 0.8594363331794739, "max": 2.849325180053711, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8375.0009765625, "min": 8205.3515625, "max": 29273.966796875, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.87205696105957, "min": 0.30252501368522644, "max": 13.87205696105957, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2843.771728515625, "min": 58.689849853515625, "max": 2843.771728515625, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07113034120496142, "min": 0.06241723957366904, "max": 0.07546684495402803, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3556517060248071, "min": 0.24966895829467617, "max": 0.3773342247701401, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1565871076198185, "min": 0.14279651935486232, "max": 0.25389921836993273, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7829355380990926, "min": 0.5711860774194493, "max": 1.2694960918496636, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.088009898240004e-05, "min": 5.088009898240004e-05, "max": 0.0049458800010823995, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0002544004949120002, "min": 0.0002544004949120002, "max": 0.024234400015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1010176, "min": 0.1010176, "max": 0.19891760000000003, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.505088, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.70909090909091, "min": 3.227272727272727, "max": 27.613636363636363, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1469.0, "min": 142.0, "max": 1483.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.70909090909091, "min": 3.227272727272727, "max": 27.613636363636363, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1469.0, "min": 142.0, "max": 1483.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705345984", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705347315" }, "total": 1330.24315613, "count": 1, "self": 0.323616249999759, "children": { "run_training.setup": { "total": 0.10072283699992113, "count": 1, "self": 0.10072283699992113 }, "TrainerController.start_learning": { "total": 1329.8188170430003, "count": 1, "self": 1.2620612559439905, "children": { "TrainerController._reset_env": { "total": 1.9207464549999713, "count": 1, "self": 1.9207464549999713 }, "TrainerController.advance": { "total": 1326.5405299470567, "count": 45479, "self": 0.6798995370691046, "children": { "env_step": { "total": 1325.8606304099876, "count": 45479, "self": 916.7325188350942, "children": { "SubprocessEnvManager._take_step": { "total": 408.45047557687303, "count": 45479, "self": 3.42435605398623, "children": { "TorchPolicy.evaluate": { "total": 405.0261195228868, "count": 45479, "self": 405.0261195228868 } } }, "workers": { "total": 0.6776359980203779, "count": 45479, "self": 0.0, "children": { "worker_root": { "total": 1328.1743440158443, "count": 45479, "is_parallel": true, "self": 809.5313830728228, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025709519995871233, "count": 1, "is_parallel": true, "self": 0.0007289020013558911, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018420499982312322, "count": 10, "is_parallel": true, "self": 0.0018420499982312322 } } }, "UnityEnvironment.step": { "total": 0.034054634000312944, "count": 1, "is_parallel": true, "self": 0.0005925420009589288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004895080001006136, "count": 1, "is_parallel": true, "self": 0.0004895080001006136 }, "communicator.exchange": { "total": 0.030629098999270354, "count": 1, "is_parallel": true, "self": 0.030629098999270354 }, "steps_from_proto": { "total": 0.0023434849999830476, "count": 1, "is_parallel": true, "self": 0.0004208880009173299, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019225969990657177, "count": 10, "is_parallel": true, "self": 0.0019225969990657177 } } } } } } }, "UnityEnvironment.step": { "total": 518.6429609430215, "count": 45478, "is_parallel": true, "self": 24.71779984413206, "children": { "UnityEnvironment._generate_step_input": { "total": 15.096978749968002, "count": 45478, "is_parallel": true, "self": 15.096978749968002 }, "communicator.exchange": { "total": 389.6918516379965, "count": 45478, "is_parallel": true, "self": 389.6918516379965 }, "steps_from_proto": { "total": 89.136330710925, "count": 45478, "is_parallel": true, "self": 15.171048562036049, "children": { "_process_rank_one_or_two_observation": { "total": 73.96528214888895, "count": 454780, "is_parallel": true, "self": 73.96528214888895 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017912499970407225, "count": 1, "self": 0.00017912499970407225, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1320.6514453061664, "count": 695674, "is_parallel": true, "self": 17.284880586615145, "children": { "process_trajectory": { "total": 600.7120704955487, "count": 695674, "is_parallel": true, "self": 599.3360110485492, "children": { "RLTrainer._checkpoint": { "total": 1.376059446999534, "count": 10, "is_parallel": true, "self": 1.376059446999534 } } }, "_update_policy": { "total": 702.6544942240025, "count": 227, "is_parallel": true, "self": 292.07694558103594, "children": { "TorchPPOOptimizer.update": { "total": 410.5775486429666, "count": 19290, "is_parallel": true, "self": 410.5775486429666 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09530025999993086, "count": 1, "self": 0.0009846299999480834, "children": { "RLTrainer._checkpoint": { "total": 0.09431562999998278, "count": 1, "self": 0.09431562999998278 } } } } } } }