{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0678207874298096, "min": 1.0678207874298096, "max": 2.8581292629241943, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10195.552734375, "min": 10195.552734375, "max": 29332.98046875, "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": 12.921195030212402, "min": 0.27218833565711975, "max": 12.921195030212402, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.633056640625, "min": 52.80453872680664, "max": 2617.89990234375, "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": 0.07312166173120632, "min": 0.06178125729978394, "max": 0.07537510915027074, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2924866469248253, "min": 0.2568251633732443, "max": 0.37216526463481725, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22200792458127527, "min": 0.10673729717781694, "max": 0.29624031747088714, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8880316983251011, "min": 0.42694918871126775, "max": 1.4812015873544357, "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": 25.863636363636363, "min": 3.1136363636363638, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1138.0, "min": 137.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.863636363636363, "min": 3.1136363636363638, "max": 25.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1138.0, "min": 137.0, "max": 1413.0, "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": "1687141343", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687141824" }, "total": 481.1920376009998, "count": 1, "self": 0.43649281199986945, "children": { "run_training.setup": { "total": 0.042650419999972655, "count": 1, "self": 0.042650419999972655 }, "TrainerController.start_learning": { "total": 480.71289436899997, "count": 1, "self": 0.5628289770083938, "children": { "TrainerController._reset_env": { "total": 4.088549951999994, "count": 1, "self": 4.088549951999994 }, "TrainerController.advance": { "total": 475.9162801089915, "count": 18202, "self": 0.27658391597469745, "children": { "env_step": { "total": 475.6396961930168, "count": 18202, "self": 347.8958137040363, "children": { "SubprocessEnvManager._take_step": { "total": 127.46664018700994, "count": 18202, "self": 1.8633602740374045, "children": { "TorchPolicy.evaluate": { "total": 125.60327991297254, "count": 18202, "self": 125.60327991297254 } } }, "workers": { "total": 0.27724230197054567, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 479.0129316449925, "count": 18202, "is_parallel": true, "self": 222.25085345497973, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005754282999987481, "count": 1, "is_parallel": true, "self": 0.004173490000994207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015807929989932745, "count": 10, "is_parallel": true, "self": 0.0015807929989932745 } } }, "UnityEnvironment.step": { "total": 0.10163862699982928, "count": 1, "is_parallel": true, "self": 0.0006299520000538905, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004237260000081733, "count": 1, "is_parallel": true, "self": 0.0004237260000081733 }, "communicator.exchange": { "total": 0.09845263299985163, "count": 1, "is_parallel": true, "self": 0.09845263299985163 }, "steps_from_proto": { "total": 0.0021323159999155905, "count": 1, "is_parallel": true, "self": 0.0004289379990041198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017033780009114707, "count": 10, "is_parallel": true, "self": 0.0017033780009114707 } } } } } } }, "UnityEnvironment.step": { "total": 256.76207819001274, "count": 18201, "is_parallel": true, "self": 10.57960317504876, "children": { "UnityEnvironment._generate_step_input": { "total": 5.527493380963733, "count": 18201, "is_parallel": true, "self": 5.527493380963733 }, "communicator.exchange": { "total": 204.07103867900787, "count": 18201, "is_parallel": true, "self": 204.07103867900787 }, "steps_from_proto": { "total": 36.58394295499238, "count": 18201, "is_parallel": true, "self": 6.718068401946766, "children": { "_process_rank_one_or_two_observation": { "total": 29.865874553045614, "count": 182010, "is_parallel": true, "self": 29.865874553045614 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016168399997695815, "count": 1, "self": 0.00016168399997695815, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.2425705389105, "count": 459808, "is_parallel": true, "self": 9.94870532090772, "children": { "process_trajectory": { "total": 260.3146476750003, "count": 459808, "is_parallel": true, "self": 259.5257709290004, "children": { "RLTrainer._checkpoint": { "total": 0.7888767459999144, "count": 4, "is_parallel": true, "self": 0.7888767459999144 } } }, "_update_policy": { "total": 201.9792175430025, "count": 90, "is_parallel": true, "self": 77.10088975701638, "children": { "TorchPPOOptimizer.update": { "total": 124.87832778598613, "count": 4587, "is_parallel": true, "self": 124.87832778598613 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1450736470001175, "count": 1, "self": 0.0008813050003482203, "children": { "RLTrainer._checkpoint": { "total": 0.14419234199976927, "count": 1, "self": 0.14419234199976927 } } } } } } }