{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9101355075836182, "min": 0.9101355075836182, "max": 2.863675355911255, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8740.03125, "min": 8740.03125, "max": 29389.900390625, "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": 12.600378036499023, "min": 0.4572647213935852, "max": 12.600378036499023, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2457.07373046875, "min": 88.70935821533203, "max": 2542.15869140625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07036330779060247, "min": 0.06096080755763551, "max": 0.07547394927721197, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2814532311624099, "min": 0.260426340568765, "max": 0.37159674653162306, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21622704846017501, "min": 0.11920348365731795, "max": 0.2639902239190597, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8649081938407001, "min": 0.4768139346292718, "max": 1.2716702263729247, "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": 25.068181818181817, "min": 3.3863636363636362, "max": 25.30909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 149.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 3.3863636363636362, "max": 25.30909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 149.0, "max": 1392.0, "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": "1679611629", "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": "1679612247" }, "total": 618.086910277, "count": 1, "self": 0.960332279000113, "children": { "run_training.setup": { "total": 0.2724483840000005, "count": 1, "self": 0.2724483840000005 }, "TrainerController.start_learning": { "total": 616.8541296139999, "count": 1, "self": 0.8603482780050626, "children": { "TrainerController._reset_env": { "total": 7.92753704499998, "count": 1, "self": 7.92753704499998 }, "TrainerController.advance": { "total": 607.8242114519949, "count": 18227, "self": 0.44509684799891147, "children": { "env_step": { "total": 607.379114603996, "count": 18227, "self": 489.27977237499755, "children": { "SubprocessEnvManager._take_step": { "total": 117.6532292859979, "count": 18227, "self": 3.2773616769939053, "children": { "TorchPolicy.evaluate": { "total": 114.37586760900399, "count": 18227, "self": 114.37586760900399 } } }, "workers": { "total": 0.4461129430005144, "count": 18227, "self": 0.0, "children": { "worker_root": { "total": 614.6191459549995, "count": 18227, "is_parallel": true, "self": 273.86228564100065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00803502599998751, "count": 1, "is_parallel": true, "self": 0.00528598999994756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027490360000399505, "count": 10, "is_parallel": true, "self": 0.0027490360000399505 } } }, "UnityEnvironment.step": { "total": 0.04720649500001173, "count": 1, "is_parallel": true, "self": 0.0006540100000052007, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003531609999924967, "count": 1, "is_parallel": true, "self": 0.0003531609999924967 }, "communicator.exchange": { "total": 0.04393490699999347, "count": 1, "is_parallel": true, "self": 0.04393490699999347 }, "steps_from_proto": { "total": 0.0022644170000205577, "count": 1, "is_parallel": true, "self": 0.00044833299998003895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018160840000405187, "count": 10, "is_parallel": true, "self": 0.0018160840000405187 } } } } } } }, "UnityEnvironment.step": { "total": 340.7568603139988, "count": 18226, "is_parallel": true, "self": 13.863562789995854, "children": { "UnityEnvironment._generate_step_input": { "total": 7.45057326300369, "count": 18226, "is_parallel": true, "self": 7.45057326300369 }, "communicator.exchange": { "total": 274.09009761800075, "count": 18226, "is_parallel": true, "self": 274.09009761800075 }, "steps_from_proto": { "total": 45.35262664299853, "count": 18226, "is_parallel": true, "self": 9.559393856994546, "children": { "_process_rank_one_or_two_observation": { "total": 35.79323278600398, "count": 182260, "is_parallel": true, "self": 35.79323278600398 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014414699990084046, "count": 1, "self": 0.00014414699990084046, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 602.0706162429918, "count": 589007, "is_parallel": true, "self": 16.701200186998676, "children": { "process_trajectory": { "total": 326.62475522099305, "count": 589007, "is_parallel": true, "self": 324.36209666999304, "children": { "RLTrainer._checkpoint": { "total": 2.2626585510000154, "count": 4, "is_parallel": true, "self": 2.2626585510000154 } } }, "_update_policy": { "total": 258.7446608350001, "count": 90, "is_parallel": true, "self": 87.11451046600334, "children": { "TorchPPOOptimizer.update": { "total": 171.63015036899677, "count": 4587, "is_parallel": true, "self": 171.63015036899677 } } } } } } } } }, "TrainerController._save_models": { "total": 0.24188869200008867, "count": 1, "self": 0.0014934710000034102, "children": { "RLTrainer._checkpoint": { "total": 0.24039522100008526, "count": 1, "self": 0.24039522100008526 } } } } } } }