{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9585409164428711, "min": 0.9585409164428711, "max": 2.8684895038604736, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9194.32421875, "min": 9194.32421875, "max": 29407.75390625, "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": 2.6107730865478516, "min": 0.2650679349899292, "max": 2.6107730865478516, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 509.10076904296875, "min": 51.423179626464844, "max": 530.3726806640625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06515976702973834, "min": 0.06287218069754126, "max": 0.07590302116219105, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2606390681189534, "min": 0.2542963077053976, "max": 0.3789707444679259, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13985315228209777, "min": 0.06858469296118938, "max": 0.16423468105494976, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5594126091283911, "min": 0.2743387718447575, "max": 0.8210403694241655, "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": 25.818181818181817, "min": 3.4318181818181817, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 151.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 3.4318181818181817, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 151.0, "max": 1408.0, "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": "1684909696", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 --torch-device cuda:0", "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": "1684910147" }, "total": 450.4638984989999, "count": 1, "self": 0.5328129629999694, "children": { "run_training.setup": { "total": 0.0484440769999992, "count": 1, "self": 0.0484440769999992 }, "TrainerController.start_learning": { "total": 449.88264145899996, "count": 1, "self": 0.560097766000581, "children": { "TrainerController._reset_env": { "total": 3.819870327999979, "count": 1, "self": 3.819870327999979 }, "TrainerController.advance": { "total": 445.29588299999944, "count": 18221, "self": 0.2530308779984125, "children": { "env_step": { "total": 445.042852122001, "count": 18221, "self": 326.0631458539914, "children": { "SubprocessEnvManager._take_step": { "total": 118.7229820190073, "count": 18221, "self": 1.7260712269968508, "children": { "TorchPolicy.evaluate": { "total": 116.99691079201045, "count": 18221, "self": 116.99691079201045 } } }, "workers": { "total": 0.2567242490023318, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 448.31404838900335, "count": 18221, "is_parallel": true, "self": 209.96925779099683, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0057790030000433035, "count": 1, "is_parallel": true, "self": 0.004392156000108116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013868469999351873, "count": 10, "is_parallel": true, "self": 0.0013868469999351873 } } }, "UnityEnvironment.step": { "total": 0.03563163600006192, "count": 1, "is_parallel": true, "self": 0.0005682740001020647, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031835899994803185, "count": 1, "is_parallel": true, "self": 0.00031835899994803185 }, "communicator.exchange": { "total": 0.032711403999996946, "count": 1, "is_parallel": true, "self": 0.032711403999996946 }, "steps_from_proto": { "total": 0.002033599000014874, "count": 1, "is_parallel": true, "self": 0.00037669000005280395, "children": { "_process_rank_one_or_two_observation": { "total": 0.00165690899996207, "count": 10, "is_parallel": true, "self": 0.00165690899996207 } } } } } } }, "UnityEnvironment.step": { "total": 238.3447905980065, "count": 18220, "is_parallel": true, "self": 9.295122522000383, "children": { "UnityEnvironment._generate_step_input": { "total": 5.140116177000209, "count": 18220, "is_parallel": true, "self": 5.140116177000209 }, "communicator.exchange": { "total": 192.08288024299486, "count": 18220, "is_parallel": true, "self": 192.08288024299486 }, "steps_from_proto": { "total": 31.826671656011058, "count": 18220, "is_parallel": true, "self": 6.045278355034611, "children": { "_process_rank_one_or_two_observation": { "total": 25.781393300976447, "count": 182200, "is_parallel": true, "self": 25.781393300976447 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013992999993206467, "count": 1, "self": 0.00013992999993206467, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 441.9713972670113, "count": 424804, "is_parallel": true, "self": 9.285131681991516, "children": { "process_trajectory": { "total": 242.60245220501884, "count": 424804, "is_parallel": true, "self": 241.45797237301883, "children": { "RLTrainer._checkpoint": { "total": 1.1444798320000018, "count": 4, "is_parallel": true, "self": 1.1444798320000018 } } }, "_update_policy": { "total": 190.08381338000095, "count": 90, "is_parallel": true, "self": 72.08808552699554, "children": { "TorchPPOOptimizer.update": { "total": 117.9957278530054, "count": 4587, "is_parallel": true, "self": 117.9957278530054 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20665043500002866, "count": 1, "self": 0.001106475000028695, "children": { "RLTrainer._checkpoint": { "total": 0.20554395999999997, "count": 1, "self": 0.20554395999999997 } } } } } } }