{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.926809549331665, "min": 0.926809549331665, "max": 2.857665538787842, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8849.177734375, "min": 8849.177734375, "max": 29265.3515625, "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": 12.978372573852539, "min": 0.39836305379867554, "max": 12.978372573852539, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2530.78271484375, "min": 77.28243255615234, "max": 2627.1064453125, "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": 0.06838249465662931, "min": 0.06282563334453324, "max": 0.07416893749748353, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27352997862651723, "min": 0.25130253337813296, "max": 0.3664494872813092, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20831082549457458, "min": 0.1415743527091656, "max": 0.26697369042564845, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8332433019782983, "min": 0.5662974108366624, "max": 1.3348684521282421, "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": 25.113636363636363, "min": 3.6818181818181817, "max": 25.8, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 162.0, "max": 1419.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.6818181818181817, "max": 25.8, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 162.0, "max": 1419.0, "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": "1721569851", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1721570303" }, "total": 451.48792095399995, "count": 1, "self": 0.4400073449999127, "children": { "run_training.setup": { "total": 0.05689697700006491, "count": 1, "self": 0.05689697700006491 }, "TrainerController.start_learning": { "total": 450.99101663199997, "count": 1, "self": 0.5840303150022237, "children": { "TrainerController._reset_env": { "total": 2.639855318000059, "count": 1, "self": 2.639855318000059 }, "TrainerController.advance": { "total": 447.6766118729978, "count": 18200, "self": 0.2694133399934344, "children": { "env_step": { "total": 447.40719853300436, "count": 18200, "self": 290.3521996700018, "children": { "SubprocessEnvManager._take_step": { "total": 156.77820007499815, "count": 18200, "self": 1.4569780980016276, "children": { "TorchPolicy.evaluate": { "total": 155.32122197699653, "count": 18200, "self": 155.32122197699653 } } }, "workers": { "total": 0.27679878800438473, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 449.5676954280119, "count": 18200, "is_parallel": true, "self": 228.49226164201343, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005384974999969927, "count": 1, "is_parallel": true, "self": 0.003844477999564333, "children": { "_process_rank_one_or_two_observation": { "total": 0.001540497000405594, "count": 10, "is_parallel": true, "self": 0.001540497000405594 } } }, "UnityEnvironment.step": { "total": 0.03460597000002963, "count": 1, "is_parallel": true, "self": 0.0006494089999478092, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040046900005563657, "count": 1, "is_parallel": true, "self": 0.00040046900005563657 }, "communicator.exchange": { "total": 0.03169715299998188, "count": 1, "is_parallel": true, "self": 0.03169715299998188 }, "steps_from_proto": { "total": 0.0018589390000443018, "count": 1, "is_parallel": true, "self": 0.0003860260001147253, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014729129999295765, "count": 10, "is_parallel": true, "self": 0.0014729129999295765 } } } } } } }, "UnityEnvironment.step": { "total": 221.07543378599848, "count": 18199, "is_parallel": true, "self": 9.958196290000501, "children": { "UnityEnvironment._generate_step_input": { "total": 5.332433040997785, "count": 18199, "is_parallel": true, "self": 5.332433040997785 }, "communicator.exchange": { "total": 172.4749267350021, "count": 18199, "is_parallel": true, "self": 172.4749267350021 }, "steps_from_proto": { "total": 33.3098777199981, "count": 18199, "is_parallel": true, "self": 6.320050849004019, "children": { "_process_rank_one_or_two_observation": { "total": 26.98982687099408, "count": 181990, "is_parallel": true, "self": 26.98982687099408 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010990399982802046, "count": 1, "self": 0.00010990399982802046, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 442.3273252609557, "count": 672707, "is_parallel": true, "self": 14.058385495020048, "children": { "process_trajectory": { "total": 243.77072294493644, "count": 672707, "is_parallel": true, "self": 242.72488652293646, "children": { "RLTrainer._checkpoint": { "total": 1.0458364219999794, "count": 4, "is_parallel": true, "self": 1.0458364219999794 } } }, "_update_policy": { "total": 184.49821682099923, "count": 90, "is_parallel": true, "self": 59.11211146099845, "children": { "TorchPPOOptimizer.update": { "total": 125.38610536000078, "count": 4584, "is_parallel": true, "self": 125.38610536000078 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09040922200006207, "count": 1, "self": 0.00101269200013121, "children": { "RLTrainer._checkpoint": { "total": 0.08939652999993086, "count": 1, "self": 0.08939652999993086 } } } } } } }