{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9353681802749634, "min": 0.9353681802749634, "max": 2.8502347469329834, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8961.7626953125, "min": 8961.7626953125, "max": 29314.6640625, "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": 12.817675590515137, "min": 0.40891385078430176, "max": 12.817675590515137, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.44677734375, "min": 79.32928466796875, "max": 2583.448974609375, "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": 0.07074342260659928, "min": 0.06243128612008078, "max": 0.07311594418038513, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28297369042639714, "min": 0.24972514448032312, "max": 0.36557972090192564, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2083352522961065, "min": 0.12253359799140918, "max": 0.272116899052087, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.833341009184426, "min": 0.49013439196563674, "max": 1.3440582021778704, "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": 25.15909090909091, "min": 3.3863636363636362, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 149.0, "max": 1383.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.3863636363636362, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 149.0, "max": 1383.0, "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": "1706369533", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/harzad/anaconda3/envs/unity-mlagent/bin/mlagents-learn ./SnowballTarget.yaml --env=./ml-agents/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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706369666" }, "total": 132.97065394800302, "count": 1, "self": 0.21684280600311467, "children": { "run_training.setup": { "total": 0.013338365002709907, "count": 1, "self": 0.013338365002709907 }, "TrainerController.start_learning": { "total": 132.7404727769972, "count": 1, "self": 0.2029068420524709, "children": { "TrainerController._reset_env": { "total": 1.5355451470022672, "count": 1, "self": 1.5355451470022672 }, "TrainerController.advance": { "total": 130.96782056194206, "count": 18204, "self": 0.08944081805384485, "children": { "env_step": { "total": 130.87837974388822, "count": 18204, "self": 93.18742509815638, "children": { "SubprocessEnvManager._take_step": { "total": 37.59113599303237, "count": 18204, "self": 0.5512243403936736, "children": { "TorchPolicy.evaluate": { "total": 37.03991165263869, "count": 18204, "self": 37.03991165263869 } } }, "workers": { "total": 0.09981865269946866, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 132.5129037762672, "count": 18204, "is_parallel": true, "self": 69.72170128911239, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012818219984183088, "count": 1, "is_parallel": true, "self": 0.0005725769806304015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007092450177879073, "count": 10, "is_parallel": true, "self": 0.0007092450177879073 } } }, "UnityEnvironment.step": { "total": 0.0119637559982948, "count": 1, "is_parallel": true, "self": 0.00016261399287031963, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00013842400221619755, "count": 1, "is_parallel": true, "self": 0.00013842400221619755 }, "communicator.exchange": { "total": 0.011184476003109012, "count": 1, "is_parallel": true, "self": 0.011184476003109012 }, "steps_from_proto": { "total": 0.00047824200009927154, "count": 1, "is_parallel": true, "self": 0.00010762498277472332, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003706170173245482, "count": 10, "is_parallel": true, "self": 0.0003706170173245482 } } } } } } }, "UnityEnvironment.step": { "total": 62.791202487154806, "count": 18203, "is_parallel": true, "self": 2.7073107168398565, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3035700617474504, "count": 18203, "is_parallel": true, "self": 1.3035700617474504 }, "communicator.exchange": { "total": 51.26839839953027, "count": 18203, "is_parallel": true, "self": 51.26839839953027 }, "steps_from_proto": { "total": 7.511923309037229, "count": 18203, "is_parallel": true, "self": 1.4750743324693758, "children": { "_process_rank_one_or_two_observation": { "total": 6.036848976567853, "count": 182030, "is_parallel": true, "self": 6.036848976567853 } } } } } } } } } } } } }, "trainer_threads": { "total": 7.402400660794228e-05, "count": 1, "self": 7.402400660794228e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 130.90621943266888, "count": 94683, "is_parallel": true, "self": 0.6359414362159441, "children": { "process_trajectory": { "total": 74.55470859047637, "count": 94683, "is_parallel": true, "self": 74.26292651947733, "children": { "RLTrainer._checkpoint": { "total": 0.29178207099903375, "count": 4, "is_parallel": true, "self": 0.29178207099903375 } } }, "_update_policy": { "total": 55.71556940597657, "count": 90, "is_parallel": true, "self": 14.28484182266402, "children": { "TorchPPOOptimizer.update": { "total": 41.430727583312546, "count": 4587, "is_parallel": true, "self": 41.430727583312546 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0341262019937858, "count": 1, "self": 0.0003828549961326644, "children": { "RLTrainer._checkpoint": { "total": 0.033743346997653134, "count": 1, "self": 0.033743346997653134 } } } } } } }