{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8437018990516663, "min": 0.8437018990516663, "max": 2.822126865386963, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8018.54296875, "min": 8018.54296875, "max": 28808.271484375, "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": 13.028243064880371, "min": 0.412729948759079, "max": 13.115806579589844, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.50732421875, "min": 80.06961059570312, "max": 2675.62451171875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0715928416773072, "min": 0.06157174554913689, "max": 0.07717571544665534, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2863713667092288, "min": 0.2557778270644371, "max": 0.36200885188893656, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23606729865366335, "min": 0.1346975036762089, "max": 0.2894128752397556, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9442691946146534, "min": 0.5387900147048356, "max": 1.3765486510945302, "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.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.Environment.CumulativeReward.mean": { "value": 24.90909090909091, "min": 3.772727272727273, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1096.0, "min": 166.0, "max": 1414.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.90909090909091, "min": 3.772727272727273, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1096.0, "min": 166.0, "max": 1414.0, "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": "1751339862", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget6 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751340305" }, "total": 442.85179600599986, "count": 1, "self": 0.4405316729998958, "children": { "run_training.setup": { "total": 0.021176423999804683, "count": 1, "self": 0.021176423999804683 }, "TrainerController.start_learning": { "total": 442.39008790900016, "count": 1, "self": 0.44945951103818516, "children": { "TrainerController._reset_env": { "total": 2.6912118239997653, "count": 1, "self": 2.6912118239997653 }, "TrainerController.advance": { "total": 439.1644211799621, "count": 18192, "self": 0.42259671100191554, "children": { "env_step": { "total": 319.49093538896886, "count": 18192, "self": 246.83324435895156, "children": { "SubprocessEnvManager._take_step": { "total": 72.40853234503174, "count": 18192, "self": 1.3330535180339211, "children": { "TorchPolicy.evaluate": { "total": 71.07547882699782, "count": 18192, "self": 71.07547882699782 } } }, "workers": { "total": 0.24915868498555938, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 440.8837808390199, "count": 18192, "is_parallel": true, "self": 225.00431562901167, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029889270003877755, "count": 1, "is_parallel": true, "self": 0.0008300410004267178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021588859999610577, "count": 10, "is_parallel": true, "self": 0.0021588859999610577 } } }, "UnityEnvironment.step": { "total": 0.08957917799989445, "count": 1, "is_parallel": true, "self": 0.000613992000126018, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038933199994062306, "count": 1, "is_parallel": true, "self": 0.00038933199994062306 }, "communicator.exchange": { "total": 0.086694523999995, "count": 1, "is_parallel": true, "self": 0.086694523999995 }, "steps_from_proto": { "total": 0.0018813299998328148, "count": 1, "is_parallel": true, "self": 0.00040066900010060635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014806609997322084, "count": 10, "is_parallel": true, "self": 0.0014806609997322084 } } } } } } }, "UnityEnvironment.step": { "total": 215.87946521000822, "count": 18191, "is_parallel": true, "self": 10.035845870977937, "children": { "UnityEnvironment._generate_step_input": { "total": 5.7807686709884365, "count": 18191, "is_parallel": true, "self": 5.7807686709884365 }, "communicator.exchange": { "total": 166.87303858603036, "count": 18191, "is_parallel": true, "self": 166.87303858603036 }, "steps_from_proto": { "total": 33.189812082011485, "count": 18191, "is_parallel": true, "self": 6.032252333039651, "children": { "_process_rank_one_or_two_observation": { "total": 27.157559748971835, "count": 181910, "is_parallel": true, "self": 27.157559748971835 } } } } } } } } } } }, "trainer_advance": { "total": 119.25088907999134, "count": 18192, "self": 0.5602205559657705, "children": { "process_trajectory": { "total": 27.32768614702718, "count": 18192, "self": 26.906036857026265, "children": { "RLTrainer._checkpoint": { "total": 0.42164929000091433, "count": 4, "self": 0.42164929000091433 } } }, "_update_policy": { "total": 91.36298237699839, "count": 90, "self": 37.64945081200494, "children": { "TorchPPOOptimizer.update": { "total": 53.713531564993445, "count": 4587, "self": 53.713531564993445 } } } } } } }, "trainer_threads": { "total": 1.3149997357686516e-06, "count": 1, "self": 1.3149997357686516e-06 }, "TrainerController._save_models": { "total": 0.08499407900035294, "count": 1, "self": 0.0008617650000815047, "children": { "RLTrainer._checkpoint": { "total": 0.08413231400027144, "count": 1, "self": 0.08413231400027144 } } } } } } }