{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0990175008773804, "min": 1.0990175008773804, "max": 2.8590903282165527, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10493.4189453125, "min": 10493.4189453125, "max": 29311.39453125, "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": 11.627962112426758, "min": 0.34431806206703186, "max": 11.627962112426758, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2267.45263671875, "min": 66.7977066040039, "max": 2350.82373046875, "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": 0.06381421406324223, "min": 0.05956455913937865, "max": 0.07187282580622088, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2552568562529689, "min": 0.2382582365575146, "max": 0.35701209792009025, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22101769910431376, "min": 0.12203321783054694, "max": 0.29455025161013887, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8840707964172551, "min": 0.48813287132218774, "max": 1.4727512580506943, "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": 22.431818181818183, "min": 3.659090909090909, "max": 22.87272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 987.0, "min": 161.0, "max": 1258.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.431818181818183, "min": 3.659090909090909, "max": 22.87272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 987.0, "min": 161.0, "max": 1258.0, "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": "1701243784", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701244282" }, "total": 497.200583411, "count": 1, "self": 0.4426694259999522, "children": { "run_training.setup": { "total": 0.05710465300001033, "count": 1, "self": 0.05710465300001033 }, "TrainerController.start_learning": { "total": 496.70080933200006, "count": 1, "self": 0.5949057750028715, "children": { "TrainerController._reset_env": { "total": 3.2373529709999502, "count": 1, "self": 3.2373529709999502 }, "TrainerController.advance": { "total": 492.76878245199737, "count": 18199, "self": 0.2760504990010304, "children": { "env_step": { "total": 492.49273195299634, "count": 18199, "self": 331.9808294389959, "children": { "SubprocessEnvManager._take_step": { "total": 160.21566476899523, "count": 18199, "self": 1.554230623988019, "children": { "TorchPolicy.evaluate": { "total": 158.6614341450072, "count": 18199, "self": 158.6614341450072 } } }, "workers": { "total": 0.2962377450052145, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 495.39929659400957, "count": 18199, "is_parallel": true, "self": 244.6484370250147, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005532072000050903, "count": 1, "is_parallel": true, "self": 0.003971362000129375, "children": { "_process_rank_one_or_two_observation": { "total": 0.001560709999921528, "count": 10, "is_parallel": true, "self": 0.001560709999921528 } } }, "UnityEnvironment.step": { "total": 0.050652911999918615, "count": 1, "is_parallel": true, "self": 0.0006822139998803323, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043594400005986245, "count": 1, "is_parallel": true, "self": 0.00043594400005986245 }, "communicator.exchange": { "total": 0.047491151000031095, "count": 1, "is_parallel": true, "self": 0.047491151000031095 }, "steps_from_proto": { "total": 0.002043602999947325, "count": 1, "is_parallel": true, "self": 0.00040518299999803276, "children": { "_process_rank_one_or_two_observation": { "total": 0.001638419999949292, "count": 10, "is_parallel": true, "self": 0.001638419999949292 } } } } } } }, "UnityEnvironment.step": { "total": 250.75085956899488, "count": 18198, "is_parallel": true, "self": 10.931027924990758, "children": { "UnityEnvironment._generate_step_input": { "total": 5.70967031700809, "count": 18198, "is_parallel": true, "self": 5.70967031700809 }, "communicator.exchange": { "total": 197.61582354899497, "count": 18198, "is_parallel": true, "self": 197.61582354899497 }, "steps_from_proto": { "total": 36.49433777800107, "count": 18198, "is_parallel": true, "self": 6.9693941720141765, "children": { "_process_rank_one_or_two_observation": { "total": 29.52494360598689, "count": 181980, "is_parallel": true, "self": 29.52494360598689 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012617099991985015, "count": 1, "self": 0.00012617099991985015, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 488.2097819410002, "count": 518933, "is_parallel": true, "self": 11.824249894031254, "children": { "process_trajectory": { "total": 275.6255958829688, "count": 518933, "is_parallel": true, "self": 274.96014028496893, "children": { "RLTrainer._checkpoint": { "total": 0.6654555979998804, "count": 4, "is_parallel": true, "self": 0.6654555979998804 } } }, "_update_policy": { "total": 200.75993616400012, "count": 90, "is_parallel": true, "self": 64.10917656000095, "children": { "TorchPPOOptimizer.update": { "total": 136.65075960399918, "count": 4587, "is_parallel": true, "self": 136.65075960399918 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09964196299995365, "count": 1, "self": 0.001056261000030645, "children": { "RLTrainer._checkpoint": { "total": 0.098585701999923, "count": 1, "self": 0.098585701999923 } } } } } } }