{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7972696423530579, "min": 0.7972696423530579, "max": 2.8693957328796387, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7621.1005859375, "min": 7621.1005859375, "max": 29385.482421875, "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": 12.898280143737793, "min": 0.2261432409286499, "max": 12.927705764770508, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.16455078125, "min": 43.871788024902344, "max": 2628.272705078125, "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": 0.07074099625962987, "min": 0.059892997334998865, "max": 0.07476645705641669, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2829639850385195, "min": 0.26898164113791767, "max": 0.3738322852820834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18745465488994822, "min": 0.10992687614292235, "max": 0.29241736554632, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7498186195597929, "min": 0.4397075045716894, "max": 1.4110524777103872, "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": 25.795454545454547, "min": 3.159090909090909, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1135.0, "min": 139.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.795454545454547, "min": 3.159090909090909, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1135.0, "min": 139.0, "max": 1418.0, "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": "1709064053", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709064479" }, "total": 425.32067691400016, "count": 1, "self": 0.5055158380000648, "children": { "run_training.setup": { "total": 0.04904546800025855, "count": 1, "self": 0.04904546800025855 }, "TrainerController.start_learning": { "total": 424.76611560799984, "count": 1, "self": 0.5386474889883175, "children": { "TrainerController._reset_env": { "total": 3.3247430090000307, "count": 1, "self": 3.3247430090000307 }, "TrainerController.advance": { "total": 420.8060031900113, "count": 18199, "self": 0.2492365579946636, "children": { "env_step": { "total": 420.55676663201666, "count": 18199, "self": 269.29651549705477, "children": { "SubprocessEnvManager._take_step": { "total": 150.9740685239476, "count": 18199, "self": 1.3922337919661913, "children": { "TorchPolicy.evaluate": { "total": 149.58183473198142, "count": 18199, "self": 149.58183473198142 } } }, "workers": { "total": 0.2861826110142829, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 423.6133918080004, "count": 18199, "is_parallel": true, "self": 212.28070976200888, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008940886000345927, "count": 1, "is_parallel": true, "self": 0.007243386000027385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016975000003185414, "count": 10, "is_parallel": true, "self": 0.0016975000003185414 } } }, "UnityEnvironment.step": { "total": 0.03647802399973443, "count": 1, "is_parallel": true, "self": 0.0007041739995656826, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004101650001757662, "count": 1, "is_parallel": true, "self": 0.0004101650001757662 }, "communicator.exchange": { "total": 0.03338524499986306, "count": 1, "is_parallel": true, "self": 0.03338524499986306 }, "steps_from_proto": { "total": 0.001978440000129922, "count": 1, "is_parallel": true, "self": 0.0003974599994762684, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015809800006536534, "count": 10, "is_parallel": true, "self": 0.0015809800006536534 } } } } } } }, "UnityEnvironment.step": { "total": 211.33268204599153, "count": 18198, "is_parallel": true, "self": 10.457894110983034, "children": { "UnityEnvironment._generate_step_input": { "total": 5.106277033002243, "count": 18198, "is_parallel": true, "self": 5.106277033002243 }, "communicator.exchange": { "total": 163.31831855196106, "count": 18198, "is_parallel": true, "self": 163.31831855196106 }, "steps_from_proto": { "total": 32.4501923500452, "count": 18198, "is_parallel": true, "self": 5.985553979107408, "children": { "_process_rank_one_or_two_observation": { "total": 26.46463837093779, "count": 181980, "is_parallel": true, "self": 26.46463837093779 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017040000011547818, "count": 1, "self": 0.00017040000011547818, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 415.4605800590725, "count": 665379, "is_parallel": true, "self": 14.015236054357501, "children": { "process_trajectory": { "total": 228.53604477271756, "count": 665379, "is_parallel": true, "self": 228.0743462227183, "children": { "RLTrainer._checkpoint": { "total": 0.4616985499992552, "count": 4, "is_parallel": true, "self": 0.4616985499992552 } } }, "_update_policy": { "total": 172.90929923199747, "count": 90, "is_parallel": true, "self": 47.91592303900961, "children": { "TorchPPOOptimizer.update": { "total": 124.99337619298785, "count": 4587, "is_parallel": true, "self": 124.99337619298785 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09655152000004819, "count": 1, "self": 0.000987370000075316, "children": { "RLTrainer._checkpoint": { "total": 0.09556414999997287, "count": 1, "self": 0.09556414999997287 } } } } } } }