{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9364668726921082, "min": 0.9217098951339722, "max": 2.859710216522217, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8941.3857421875, "min": 8941.3857421875, "max": 29286.29296875, "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": 12.876825332641602, "min": 0.3688676953315735, "max": 12.876825332641602, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2510.98095703125, "min": 71.56033325195312, "max": 2608.50390625, "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": 0.06760396189444388, "min": 0.0637441216517176, "max": 0.07422698918318002, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27041584757777554, "min": 0.2549764866068704, "max": 0.37113494591590007, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.216800403361227, "min": 0.10837355297739051, "max": 0.30169234103431886, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.867201613444908, "min": 0.43349421190956205, "max": 1.4335591024627872, "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": 25.136363636363637, "min": 3.3863636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 149.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 3.3863636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 149.0, "max": 1390.0, "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": "1679032048", "python_version": "3.7.12 | packaged by conda-forge | (default, Oct 26 2021, 06:08:53) \n[GCC 9.4.0]", "command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "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": "1679032558" }, "total": 510.827057859, "count": 1, "self": 0.444883536999896, "children": { "run_training.setup": { "total": 0.8465792510000938, "count": 1, "self": 0.8465792510000938 }, "TrainerController.start_learning": { "total": 509.535595071, "count": 1, "self": 0.6153003779941173, "children": { "TrainerController._reset_env": { "total": 9.845046780000303, "count": 1, "self": 9.845046780000303 }, "TrainerController.advance": { "total": 498.92488214400555, "count": 18203, "self": 0.3442750300055195, "children": { "env_step": { "total": 498.58060711400003, "count": 18203, "self": 323.7209836109905, "children": { "SubprocessEnvManager._take_step": { "total": 174.56473324799526, "count": 18203, "self": 1.6298919550008577, "children": { "TorchPolicy.evaluate": { "total": 172.9348412929944, "count": 18203, "self": 38.980232848979995, "children": { "TorchPolicy.sample_actions": { "total": 133.9546084440144, "count": 18203, "self": 133.9546084440144 } } } } }, "workers": { "total": 0.29489025501425203, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 508.9059784620381, "count": 18203, "is_parallel": true, "self": 255.88361268505423, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005553119000069273, "count": 1, "is_parallel": true, "self": 0.0027319190003254334, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028211999997438397, "count": 10, "is_parallel": true, "self": 0.0028211999997438397 } } }, "UnityEnvironment.step": { "total": 0.08364721299994926, "count": 1, "is_parallel": true, "self": 0.0007697430000916938, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004804140003216162, "count": 1, "is_parallel": true, "self": 0.0004804140003216162 }, "communicator.exchange": { "total": 0.07919512399985251, "count": 1, "is_parallel": true, "self": 0.07919512399985251 }, "steps_from_proto": { "total": 0.0032019319996834383, "count": 1, "is_parallel": true, "self": 0.0007854279992898228, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024165040003936156, "count": 10, "is_parallel": true, "self": 0.0024165040003936156 } } } } } } }, "UnityEnvironment.step": { "total": 253.02236577698386, "count": 18202, "is_parallel": true, "self": 10.480323736972423, "children": { "UnityEnvironment._generate_step_input": { "total": 6.489388697973027, "count": 18202, "is_parallel": true, "self": 6.489388697973027 }, "communicator.exchange": { "total": 198.01245343000755, "count": 18202, "is_parallel": true, "self": 198.01245343000755 }, "steps_from_proto": { "total": 38.04019991203086, "count": 18202, "is_parallel": true, "self": 8.803405002010095, "children": { "_process_rank_one_or_two_observation": { "total": 29.236794910020762, "count": 182020, "is_parallel": true, "self": 29.236794910020762 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020348499992906, "count": 1, "self": 0.00020348499992906, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 493.83825296096074, "count": 437019, "is_parallel": true, "self": 15.323814949717416, "children": { "process_trajectory": { "total": 281.24327330524284, "count": 437019, "is_parallel": true, "self": 280.04849365924247, "children": { "RLTrainer._checkpoint": { "total": 1.1947796460003701, "count": 4, "is_parallel": true, "self": 1.1947796460003701 } } }, "_update_policy": { "total": 197.2711647060005, "count": 90, "is_parallel": true, "self": 61.911275402989304, "children": { "TorchPPOOptimizer.update": { "total": 135.3598893030112, "count": 4587, "is_parallel": true, "self": 135.3598893030112 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15016228400008913, "count": 1, "self": 0.0012087549998796021, "children": { "RLTrainer._checkpoint": { "total": 0.14895352900020953, "count": 1, "self": 0.14895352900020953 } } } } } } }