{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9923771619796753, "min": 0.9923771619796753, "max": 2.8786134719848633, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9780.869140625, "min": 9780.869140625, "max": 29384.88671875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9984.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9984.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.704163551330566, "min": 0.1418629139661789, "max": 12.704163551330566, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 4395.640625, "min": 48.94270706176758, "max": 4427.662109375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04467292573735904, "min": 0.039076253460279986, "max": 0.06054593183216639, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.17869170294943615, "min": 0.15630501384111994, "max": 0.26997842892888, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16892886254936457, "min": 0.06613010034197941, "max": 0.21004654802381992, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6757154501974583, "min": 0.26452040136791766, "max": 1.0502327401190996, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.347009730600001e-05, "min": 1.347009730600001e-05, "max": 0.00048647000270600005, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.388038922400004e-05, "min": 5.388038922400004e-05, "max": 0.00230860003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101347, "min": 0.101347, "max": 0.148647, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405388, "min": 0.405388, "max": 0.73086, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.361060000000004e-05, "min": 6.361060000000004e-05, "max": 0.0019461506, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00025444240000000015, "min": 0.00025444240000000015, "max": 0.009238228000000001, "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": 25.295454545454547, "min": 3.159090909090909, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 139.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.159090909090909, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 139.0, "max": 1405.0, "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": "1751650950", "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=SnowballTarget1 --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": "1751651332" }, "total": 381.4976623130001, "count": 1, "self": 0.43852351800023825, "children": { "run_training.setup": { "total": 0.023029425000004267, "count": 1, "self": 0.023029425000004267 }, "TrainerController.start_learning": { "total": 381.03610936999985, "count": 1, "self": 0.34940780001579697, "children": { "TrainerController._reset_env": { "total": 3.1115399860000252, "count": 1, "self": 3.1115399860000252 }, "TrainerController.advance": { "total": 377.486965160984, "count": 18192, "self": 0.38934625599881656, "children": { "env_step": { "total": 298.3649773470072, "count": 18192, "self": 230.44357231299205, "children": { "SubprocessEnvManager._take_step": { "total": 67.71243508802218, "count": 18192, "self": 1.2311744800231281, "children": { "TorchPolicy.evaluate": { "total": 66.48126060799905, "count": 18192, "self": 66.48126060799905 } } }, "workers": { "total": 0.20896994599297614, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 379.62575990800724, "count": 18192, "is_parallel": true, "self": 177.38157260200478, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005124139999907129, "count": 1, "is_parallel": true, "self": 0.0035729460003040003, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015511939996031288, "count": 10, "is_parallel": true, "self": 0.0015511939996031288 } } }, "UnityEnvironment.step": { "total": 0.03471657199997935, "count": 1, "is_parallel": true, "self": 0.0005871600001228217, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041499799999655806, "count": 1, "is_parallel": true, "self": 0.00041499799999655806 }, "communicator.exchange": { "total": 0.03186053599984007, "count": 1, "is_parallel": true, "self": 0.03186053599984007 }, "steps_from_proto": { "total": 0.001853878000019904, "count": 1, "is_parallel": true, "self": 0.00036100499914937245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014928730008705315, "count": 10, "is_parallel": true, "self": 0.0014928730008705315 } } } } } } }, "UnityEnvironment.step": { "total": 202.24418730600246, "count": 18191, "is_parallel": true, "self": 9.872606642018582, "children": { "UnityEnvironment._generate_step_input": { "total": 5.339244836973421, "count": 18191, "is_parallel": true, "self": 5.339244836973421 }, "communicator.exchange": { "total": 155.33375647001048, "count": 18191, "is_parallel": true, "self": 155.33375647001048 }, "steps_from_proto": { "total": 31.69857935699997, "count": 18191, "is_parallel": true, "self": 5.712093120998588, "children": { "_process_rank_one_or_two_observation": { "total": 25.986486236001383, "count": 181910, "is_parallel": true, "self": 25.986486236001383 } } } } } } } } } } }, "trainer_advance": { "total": 78.73264155797801, "count": 18192, "self": 0.44047083495820516, "children": { "process_trajectory": { "total": 34.03118784001913, "count": 18192, "self": 33.61856329201942, "children": { "RLTrainer._checkpoint": { "total": 0.4126245479997124, "count": 4, "self": 0.4126245479997124 } } }, "_update_policy": { "total": 44.26098288300068, "count": 90, "self": 25.78638502399872, "children": { "TorchPPOOptimizer.update": { "total": 18.47459785900196, "count": 1440, "self": 18.47459785900196 } } } } } } }, "trainer_threads": { "total": 1.1090000953117851e-06, "count": 1, "self": 1.1090000953117851e-06 }, "TrainerController._save_models": { "total": 0.0881953139999041, "count": 1, "self": 0.0008131259999117901, "children": { "RLTrainer._checkpoint": { "total": 0.08738218799999231, "count": 1, "self": 0.08738218799999231 } } } } } } }