{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.0383450984954834, "min": 1.0383450984954834, "max": 1.418938398361206, "count": 167 }, "Worm.Policy.Entropy.sum": { "value": 31150.3515625, "min": 31150.3515625, "max": 42568.15234375, "count": 167 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 167 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 167 }, "Worm.Step.mean": { "value": 5009000.0, "min": 29000.0, "max": 5009000.0, "count": 167 }, "Worm.Step.sum": { "value": 5009000.0, "min": 29000.0, "max": 5009000.0, "count": 167 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 911.670166015625, "min": -0.027795789763331413, "max": 911.670166015625, "count": 167 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 27350.10546875, "min": -0.8338736891746521, "max": 27350.10546875, "count": 167 }, "Worm.Environment.CumulativeReward.mean": { "value": 805.3793802897136, "min": 0.29938842456710213, "max": 805.3793802897136, "count": 167 }, "Worm.Environment.CumulativeReward.sum": { "value": 24161.381408691406, "min": 8.981652737013064, "max": 24161.381408691406, "count": 167 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 805.3793802897136, "min": 0.29938842456710213, "max": 805.3793802897136, "count": 167 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 24161.381408691406, "min": 8.981652737013064, "max": 24161.381408691406, "count": 167 }, "Worm.IsTraining.mean": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 167 }, "Worm.IsTraining.sum": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 167 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01523660916427616, "min": 0.012222255894725788, "max": 0.022566866207246978, "count": 166 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01523660916427616, "min": 0.012222255894725788, "max": 0.022566866207246978, "count": 166 }, "Worm.Losses.ValueLoss.mean": { "value": 86.60273052397228, "min": 0.0016061962122053263, "max": 86.60273052397228, "count": 166 }, "Worm.Losses.ValueLoss.sum": { "value": 86.60273052397228, "min": 0.0016061962122053263, "max": 86.60273052397228, "count": 166 }, "Worm.Policy.LearningRate.mean": { "value": 1.200099600000001e-06, "min": 1.200099600000001e-06, "max": 0.0002982000005999999, "count": 166 }, "Worm.Policy.LearningRate.sum": { "value": 1.200099600000001e-06, "min": 1.200099600000001e-06, "max": 0.0002982000005999999, "count": 166 }, "Worm.Policy.Epsilon.mean": { "value": 0.10039999999999998, "min": 0.10039999999999998, "max": 0.19940000000000005, "count": 166 }, "Worm.Policy.Epsilon.sum": { "value": 0.10039999999999998, "min": 0.10039999999999998, "max": 0.19940000000000005, "count": 166 }, "Worm.Policy.Beta.mean": { "value": 2.996000000000002e-05, "min": 2.996000000000002e-05, "max": 0.00497006, "count": 166 }, "Worm.Policy.Beta.sum": { "value": 2.996000000000002e-05, "min": 2.996000000000002e-05, "max": 0.00497006, "count": 166 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714641014", "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/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=Worm2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714648964" }, "total": 7950.43931719, "count": 1, "self": 0.27240052500019374, "children": { "run_training.setup": { "total": 0.03199088000019401, "count": 1, "self": 0.03199088000019401 }, "TrainerController.start_learning": { "total": 7950.134925785, "count": 1, "self": 6.8739123757559355, "children": { "TrainerController._reset_env": { "total": 3.6837898109997695, "count": 1, "self": 3.6837898109997695 }, "TrainerController.advance": { "total": 7939.347177344245, "count": 501000, "self": 6.619951957754893, "children": { "env_step": { "total": 7158.685518757587, "count": 501000, "self": 3641.34230069079, "children": { "SubprocessEnvManager._take_step": { "total": 3512.991070379864, "count": 501000, "self": 36.804414690867816, "children": { "TorchPolicy.evaluate": { "total": 3476.1866556889963, "count": 501000, "self": 3476.1866556889963 } } }, "workers": { "total": 4.352147686932312, "count": 501000, "self": 0.0, "children": { "worker_root": { "total": 7933.499011418997, "count": 501000, "is_parallel": true, "self": 4684.752994616309, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008045820000006643, "count": 1, "is_parallel": true, "self": 0.0001709239995761891, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006336580004244752, "count": 2, "is_parallel": true, "self": 0.0006336580004244752 } } }, "UnityEnvironment.step": { "total": 0.019127113000195095, "count": 1, "is_parallel": true, "self": 0.00013211299983595381, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002480969997122884, "count": 1, "is_parallel": true, "self": 0.0002480969997122884 }, "communicator.exchange": { "total": 0.018405206000352337, "count": 1, "is_parallel": true, "self": 0.018405206000352337 }, "steps_from_proto": { "total": 0.00034169700029451633, "count": 1, "is_parallel": true, "self": 0.00013287599995237542, "children": { "_process_rank_one_or_two_observation": { "total": 0.0002088210003421409, "count": 2, "is_parallel": true, "self": 0.0002088210003421409 } } } } } } }, "UnityEnvironment.step": { "total": 3248.746016802688, "count": 500999, "is_parallel": true, "self": 38.527613540150924, "children": { "UnityEnvironment._generate_step_input": { "total": 53.303079868708664, "count": 500999, "is_parallel": true, "self": 53.303079868708664 }, "communicator.exchange": { "total": 3074.0460657642343, "count": 500999, "is_parallel": true, "self": 3074.0460657642343 }, "steps_from_proto": { "total": 82.8692576295939, "count": 500999, "is_parallel": true, "self": 27.10341265893203, "children": { "_process_rank_one_or_two_observation": { "total": 55.765844970661874, "count": 1001998, "is_parallel": true, "self": 55.765844970661874 } } } } } } } } } } }, "trainer_advance": { "total": 774.0417066289033, "count": 501000, "self": 7.8497958482385, "children": { "process_trajectory": { "total": 235.67155292566395, "count": 501000, "self": 233.29774147166336, "children": { "RLTrainer._checkpoint": { "total": 2.373811454000588, "count": 10, "self": 2.373811454000588 } } }, "_update_policy": { "total": 530.5203578550008, "count": 166, "self": 363.2441809010629, "children": { "TorchPPOOptimizer.update": { "total": 167.27617695393792, "count": 6972, "self": 167.27617695393792 } } } } } } }, "trainer_threads": { "total": 6.299997039604932e-07, "count": 1, "self": 6.299997039604932e-07 }, "TrainerController._save_models": { "total": 0.23004562399910355, "count": 1, "self": 0.0013605900003312854, "children": { "RLTrainer._checkpoint": { "total": 0.22868503399877227, "count": 1, "self": 0.22868503399877227 } } } } } } }