{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9485656023025513, "min": 0.9297290444374084, "max": 2.8607170581817627, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9056.904296875, "min": 9056.904296875, "max": 29516.87890625, "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": 12.09045124053955, "min": 0.5266668796539307, "max": 12.09045124053955, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2357.637939453125, "min": 102.17337799072266, "max": 2446.60595703125, "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": 0.06246662683563544, "min": 0.06246662683563544, "max": 0.072045463302821, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24986650734254176, "min": 0.24986650734254176, "max": 0.35540116288101153, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16346346407982648, "min": 0.11599406158533312, "max": 0.2654777579739982, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6538538563193059, "min": 0.4639762463413325, "max": 1.2732342534205494, "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": 23.84090909090909, "min": 3.8181818181818183, "max": 23.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1049.0, "min": 168.0, "max": 1302.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.84090909090909, "min": 3.8181818181818183, "max": 23.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1049.0, "min": 168.0, "max": 1302.0, "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": "1678813085", "python_version": "3.7.16 (default, Dec 7 2022, 01:12:19) \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 --resume", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1678813602" }, "total": 516.6174102069999, "count": 1, "self": 0.43682553800044843, "children": { "run_training.setup": { "total": 0.0283632839996244, "count": 1, "self": 0.0283632839996244 }, "TrainerController.start_learning": { "total": 516.1522213849998, "count": 1, "self": 0.6803429189867529, "children": { "TrainerController._reset_env": { "total": 5.414292310000292, "count": 1, "self": 5.414292310000292 }, "TrainerController.advance": { "total": 509.92905087501276, "count": 18202, "self": 0.37561251504712345, "children": { "env_step": { "total": 509.55343835996564, "count": 18202, "self": 358.35919256296165, "children": { "SubprocessEnvManager._take_step": { "total": 150.89714755799423, "count": 18202, "self": 1.755810969002141, "children": { "TorchPolicy.evaluate": { "total": 149.1413365889921, "count": 18202, "self": 32.49673365702074, "children": { "TorchPolicy.sample_actions": { "total": 116.64460293197135, "count": 18202, "self": 116.64460293197135 } } } } }, "workers": { "total": 0.29709823900975607, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 514.4302576730133, "count": 18202, "is_parallel": true, "self": 255.91250111201134, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003090391000114323, "count": 1, "is_parallel": true, "self": 0.001036213000134012, "children": { "_process_rank_one_or_two_observation": { "total": 0.002054177999980311, "count": 10, "is_parallel": true, "self": 0.002054177999980311 } } }, "UnityEnvironment.step": { "total": 0.06663784400006989, "count": 1, "is_parallel": true, "self": 0.0006254750001062348, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005082180000499648, "count": 1, "is_parallel": true, "self": 0.0005082180000499648 }, "communicator.exchange": { "total": 0.06233006399997976, "count": 1, "is_parallel": true, "self": 0.06233006399997976 }, "steps_from_proto": { "total": 0.003174086999933934, "count": 1, "is_parallel": true, "self": 0.0016592739993939176, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015148130005400162, "count": 10, "is_parallel": true, "self": 0.0015148130005400162 } } } } } } }, "UnityEnvironment.step": { "total": 258.517756561002, "count": 18201, "is_parallel": true, "self": 10.037608458037084, "children": { "UnityEnvironment._generate_step_input": { "total": 5.86600718997488, "count": 18201, "is_parallel": true, "self": 5.86600718997488 }, "communicator.exchange": { "total": 207.567036645999, "count": 18201, "is_parallel": true, "self": 207.567036645999 }, "steps_from_proto": { "total": 35.04710426699103, "count": 18201, "is_parallel": true, "self": 8.553474335893497, "children": { "_process_rank_one_or_two_observation": { "total": 26.49362993109753, "count": 182010, "is_parallel": true, "self": 26.49362993109753 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017346300001008785, "count": 1, "self": 0.00017346300001008785, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 505.03453641603164, "count": 462304, "is_parallel": true, "self": 15.15906275511179, "children": { "process_trajectory": { "total": 284.3042427309174, "count": 462304, "is_parallel": true, "self": 282.58924854191764, "children": { "RLTrainer._checkpoint": { "total": 1.7149941889997535, "count": 4, "is_parallel": true, "self": 1.7149941889997535 } } }, "_update_policy": { "total": 205.57123093000246, "count": 90, "is_parallel": true, "self": 92.2093263159968, "children": { "TorchPPOOptimizer.update": { "total": 113.36190461400565, "count": 4587, "is_parallel": true, "self": 113.36190461400565 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12836181800003033, "count": 1, "self": 0.001240963999862288, "children": { "RLTrainer._checkpoint": { "total": 0.12712085400016804, "count": 1, "self": 0.12712085400016804 } } } } } } }