{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.3855702877044678, "min": 1.3855702877044678, "max": 1.4216307401657104, "count": 33 }, "Worm.Policy.Entropy.sum": { "value": 41567.109375, "min": 41567.109375, "max": 42648.921875, "count": 33 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 33 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 33 }, "Worm.Step.mean": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Step.sum": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 7.239400386810303, "min": 0.07958345115184784, "max": 7.239400386810303, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 217.1820068359375, "min": 2.307919979095459, "max": 217.1820068359375, "count": 33 }, "Worm.Environment.CumulativeReward.mean": { "value": 69.1140012105306, "min": 0.36864107997874573, "max": 69.1140012105306, "count": 33 }, "Worm.Environment.CumulativeReward.sum": { "value": 2073.420036315918, "min": 11.059232399362372, "max": 2073.420036315918, "count": 33 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 69.1140012105306, "min": 0.36864107997874573, "max": 69.1140012105306, "count": 33 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 2073.420036315918, "min": 11.059232399362372, "max": 2073.420036315918, "count": 33 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01700288818461732, "min": 0.012559550390592665, "max": 0.02170003344820413, "count": 32 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01700288818461732, "min": 0.012559550390592665, "max": 0.02170003344820413, "count": 32 }, "Worm.Losses.ValueLoss.mean": { "value": 0.6396481550875164, "min": 0.0015461337946665783, "max": 0.6396481550875164, "count": 32 }, "Worm.Losses.ValueLoss.sum": { "value": 0.6396481550875164, "min": 0.0015461337946665783, "max": 0.6396481550875164, "count": 32 }, "Worm.Policy.LearningRate.mean": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.LearningRate.sum": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.Epsilon.mean": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Epsilon.sum": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Beta.mean": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 }, "Worm.Policy.Beta.sum": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673594490", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673596249" }, "total": 1759.3737478989997, "count": 1, "self": 0.390409956999747, "children": { "run_training.setup": { "total": 0.1343860179999865, "count": 1, "self": 0.1343860179999865 }, "TrainerController.start_learning": { "total": 1758.848951924, "count": 1, "self": 2.8911124390392615, "children": { "TrainerController._reset_env": { "total": 11.722249229999989, "count": 1, "self": 11.722249229999989 }, "TrainerController.advance": { "total": 1744.1191414329605, "count": 101000, "self": 3.274395886034199, "children": { "env_step": { "total": 1480.5657777029633, "count": 101000, "self": 1270.740867891979, "children": { "SubprocessEnvManager._take_step": { "total": 207.63498515105084, "count": 101000, "self": 14.168415779053475, "children": { "TorchPolicy.evaluate": { "total": 193.46656937199737, "count": 101000, "self": 54.161449766959095, "children": { "TorchPolicy.sample_actions": { "total": 139.30511960503827, "count": 101000, "self": 139.30511960503827 } } } } }, "workers": { "total": 2.1899246599334674, "count": 101000, "self": 0.0, "children": { "worker_root": { "total": 1752.1385774060286, "count": 101000, "is_parallel": true, "self": 675.5021697600755, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031173570000646578, "count": 1, "is_parallel": true, "self": 0.00042032100009237183, "children": { "_process_rank_one_or_two_observation": { "total": 0.002697035999972286, "count": 2, "is_parallel": true, "self": 0.002697035999972286 } } }, "UnityEnvironment.step": { "total": 0.03844414299999244, "count": 1, "is_parallel": true, "self": 0.0003189819999533938, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048704200003157894, "count": 1, "is_parallel": true, "self": 0.00048704200003157894 }, "communicator.exchange": { "total": 0.03669263699998737, "count": 1, "is_parallel": true, "self": 0.03669263699998737 }, "steps_from_proto": { "total": 0.0009454820000200925, "count": 1, "is_parallel": true, "self": 0.0002787139999327337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006667680000873588, "count": 2, "is_parallel": true, "self": 0.0006667680000873588 } } } } } } }, "UnityEnvironment.step": { "total": 1076.636407645953, "count": 100999, "is_parallel": true, "self": 26.31573110897216, "children": { "UnityEnvironment._generate_step_input": { "total": 44.83505546201013, "count": 100999, "is_parallel": true, "self": 44.83505546201013 }, "communicator.exchange": { "total": 938.2505047979997, "count": 100999, "is_parallel": true, "self": 938.2505047979997 }, "steps_from_proto": { "total": 67.23511627697121, "count": 100999, "is_parallel": true, "self": 25.792633828914973, "children": { "_process_rank_one_or_two_observation": { "total": 41.44248244805624, "count": 201998, "is_parallel": true, "self": 41.44248244805624 } } } } } } } } } } }, "trainer_advance": { "total": 260.2789678439632, "count": 101000, "self": 4.255586039994341, "children": { "process_trajectory": { "total": 73.89419529096926, "count": 101000, "self": 73.6270702959689, "children": { "RLTrainer._checkpoint": { "total": 0.26712499500035847, "count": 2, "self": 0.26712499500035847 } } }, "_update_policy": { "total": 182.12918651299958, "count": 33, "self": 152.5630465890041, "children": { "TorchPPOOptimizer.update": { "total": 29.56613992399548, "count": 1386, "self": 29.56613992399548 } } } } } } }, "trainer_threads": { "total": 8.249999154941179e-07, "count": 1, "self": 8.249999154941179e-07 }, "TrainerController._save_models": { "total": 0.11644799700025033, "count": 1, "self": 0.002145944999938365, "children": { "RLTrainer._checkpoint": { "total": 0.11430205200031196, "count": 1, "self": 0.11430205200031196 } } } } } } }