{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8428723216056824, "min": 0.8428723216056824, "max": 2.842378854751587, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8047.7451171875, "min": 8047.7451171875, "max": 29108.80078125, "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": 12.517635345458984, "min": 0.39110851287841797, "max": 12.517635345458984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2440.93896484375, "min": 75.87505340576172, "max": 2540.947998046875, "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": 0.06852181824235552, "min": 0.06261284721075949, "max": 0.0743813681734073, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2740872729694221, "min": 0.25045138884303797, "max": 0.3719068408670365, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2300105881603325, "min": 0.12355481408417737, "max": 0.27800244575037675, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.92004235264133, "min": 0.4942192563367095, "max": 1.3391788493768844, "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": 24.977272727272727, "min": 3.5, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 154.0, "max": 1364.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.5, "max": 24.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 154.0, "max": 1364.0, "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": "1702871203", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702871652" }, "total": 448.88844775799987, "count": 1, "self": 0.4461582119997729, "children": { "run_training.setup": { "total": 0.06674715000008291, "count": 1, "self": 0.06674715000008291 }, "TrainerController.start_learning": { "total": 448.375542396, "count": 1, "self": 0.5617334819936559, "children": { "TrainerController._reset_env": { "total": 3.7674268749999555, "count": 1, "self": 3.7674268749999555 }, "TrainerController.advance": { "total": 443.9576375320064, "count": 18199, "self": 0.28294535699239987, "children": { "env_step": { "total": 443.674692175014, "count": 18199, "self": 293.33622249202756, "children": { "SubprocessEnvManager._take_step": { "total": 150.06639199001006, "count": 18199, "self": 1.432510433016546, "children": { "TorchPolicy.evaluate": { "total": 148.63388155699352, "count": 18199, "self": 148.63388155699352 } } }, "workers": { "total": 0.2720776929763815, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 447.2161362919961, "count": 18199, "is_parallel": true, "self": 218.71376027500526, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006559137000067494, "count": 1, "is_parallel": true, "self": 0.004426173000069866, "children": { "_process_rank_one_or_two_observation": { "total": 0.002132963999997628, "count": 10, "is_parallel": true, "self": 0.002132963999997628 } } }, "UnityEnvironment.step": { "total": 0.04269313700001476, "count": 1, "is_parallel": true, "self": 0.0007160399999293077, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037957500001084554, "count": 1, "is_parallel": true, "self": 0.00037957500001084554 }, "communicator.exchange": { "total": 0.039594687000089834, "count": 1, "is_parallel": true, "self": 0.039594687000089834 }, "steps_from_proto": { "total": 0.0020028349999847705, "count": 1, "is_parallel": true, "self": 0.00035855499993431295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016442800000504576, "count": 10, "is_parallel": true, "self": 0.0016442800000504576 } } } } } } }, "UnityEnvironment.step": { "total": 228.50237601699087, "count": 18198, "is_parallel": true, "self": 10.837513711960128, "children": { "UnityEnvironment._generate_step_input": { "total": 5.182042544004503, "count": 18198, "is_parallel": true, "self": 5.182042544004503 }, "communicator.exchange": { "total": 178.67494925100118, "count": 18198, "is_parallel": true, "self": 178.67494925100118 }, "steps_from_proto": { "total": 33.807870510025055, "count": 18198, "is_parallel": true, "self": 6.263975010051581, "children": { "_process_rank_one_or_two_observation": { "total": 27.543895499973473, "count": 181980, "is_parallel": true, "self": 27.543895499973473 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001915230000122392, "count": 1, "self": 0.0001915230000122392, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 438.5833274839913, "count": 664934, "is_parallel": true, "self": 13.89467663295568, "children": { "process_trajectory": { "total": 241.96387168403533, "count": 664934, "is_parallel": true, "self": 241.4883330380353, "children": { "RLTrainer._checkpoint": { "total": 0.47553864600001816, "count": 4, "is_parallel": true, "self": 0.47553864600001816 } } }, "_update_policy": { "total": 182.7247791670003, "count": 90, "is_parallel": true, "self": 57.58719910299408, "children": { "TorchPPOOptimizer.update": { "total": 125.13758006400622, "count": 4587, "is_parallel": true, "self": 125.13758006400622 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08855298399998901, "count": 1, "self": 0.0010014790000241192, "children": { "RLTrainer._checkpoint": { "total": 0.08755150499996489, "count": 1, "self": 0.08755150499996489 } } } } } } }