{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.135367512702942, "min": 1.135367512702942, "max": 2.887923240661621, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11589.83203125, "min": 10198.53515625, "max": 31862.45703125, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499912.0, "min": 9952.0, "max": 499912.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499912.0, "min": 9952.0, "max": 499912.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 2.7458341121673584, "min": 0.106269471347332, "max": 2.7458341121673584, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 277.3292541503906, "min": 10.308138847351074, "max": 278.6896057128906, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.037735849056602, "min": 3.0681818181818183, "max": 27.434782608695652, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1433.0, "min": 135.0, "max": 1457.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.037735849056602, "min": 3.0681818181818183, "max": 27.434782608695652, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1433.0, "min": 135.0, "max": 1457.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05115493647856912, "min": 0.04354346607116681, "max": 0.056254119427039236, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.05115493647856912, "min": 0.04354346607116681, "max": 0.10711522025230806, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1038912947563564, "min": 0.06381678456331001, "max": 0.16697393173680586, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.1038912947563564, "min": 0.06381678456331001, "max": 0.2940784593715387, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.5984098401599997e-05, "min": 1.5984098401599997e-05, "max": 0.00098240000176, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5984098401599997e-05, "min": 1.5984098401599997e-05, "max": 0.0017391680260832, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10159840000000002, "min": 0.10159840000000002, "max": 0.19823999999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10159840000000002, "min": 0.10159840000000002, "max": 0.3739168, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.976015999999999e-05, "min": 8.976015999999999e-05, "max": 0.004912176000000002, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.976015999999999e-05, "min": 8.976015999999999e-05, "max": 0.008698448319999998, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673953146", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1673954277" }, "total": 1130.721411611, "count": 1, "self": 0.3841987599994354, "children": { "run_training.setup": { "total": 0.11357385500014061, "count": 1, "self": 0.11357385500014061 }, "TrainerController.start_learning": { "total": 1130.2236389960003, "count": 1, "self": 1.3224685849850175, "children": { "TrainerController._reset_env": { "total": 6.175763149999966, "count": 1, "self": 6.175763149999966 }, "TrainerController.advance": { "total": 1122.606961164015, "count": 45534, "self": 0.6573774920002506, "children": { "env_step": { "total": 1121.9495836720148, "count": 45534, "self": 753.3429917339977, "children": { "SubprocessEnvManager._take_step": { "total": 367.9117610980047, "count": 45534, "self": 3.362679239029603, "children": { "TorchPolicy.evaluate": { "total": 364.5490818589751, "count": 45534, "self": 79.10298805595357, "children": { "TorchPolicy.sample_actions": { "total": 285.44609380302154, "count": 45534, "self": 285.44609380302154 } } } } }, "workers": { "total": 0.6948308400124006, "count": 45534, "self": 0.0, "children": { "worker_root": { "total": 1126.9902016269893, "count": 45534, "is_parallel": true, "self": 565.6729538380469, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018085649999193265, "count": 1, "is_parallel": true, "self": 0.0005987880003885948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012097769995307317, "count": 10, "is_parallel": true, "self": 0.0012097769995307317 } } }, "UnityEnvironment.step": { "total": 0.03667948699967383, "count": 1, "is_parallel": true, "self": 0.00035762999914368265, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000469673000225157, "count": 1, "is_parallel": true, "self": 0.000469673000225157 }, "communicator.exchange": { "total": 0.0343268070000704, "count": 1, "is_parallel": true, "self": 0.0343268070000704 }, "steps_from_proto": { "total": 0.0015253770002345846, "count": 1, "is_parallel": true, "self": 0.00040654099984749337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011188360003870912, "count": 10, "is_parallel": true, "self": 0.0011188360003870912 } } } } } } }, "UnityEnvironment.step": { "total": 561.3172477889425, "count": 45533, "is_parallel": true, "self": 20.925553688022774, "children": { "UnityEnvironment._generate_step_input": { "total": 12.946825961988452, "count": 45533, "is_parallel": true, "self": 12.946825961988452 }, "communicator.exchange": { "total": 445.0801878959833, "count": 45533, "is_parallel": true, "self": 445.0801878959833 }, "steps_from_proto": { "total": 82.364680242948, "count": 45533, "is_parallel": true, "self": 16.67430063593565, "children": { "_process_rank_one_or_two_observation": { "total": 65.69037960701235, "count": 455330, "is_parallel": true, "self": 65.69037960701235 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.785600003742729e-05, "count": 1, "self": 4.785600003742729e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1113.9459555088974, "count": 1033906, "is_parallel": true, "self": 26.339789770306652, "children": { "process_trajectory": { "total": 670.5739063215933, "count": 1033906, "is_parallel": true, "self": 668.849687068594, "children": { "RLTrainer._checkpoint": { "total": 1.724219252999319, "count": 10, "is_parallel": true, "self": 1.724219252999319 } } }, "_update_policy": { "total": 417.0322594169975, "count": 56, "is_parallel": true, "self": 179.76885711297064, "children": { "TorchPPOOptimizer.update": { "total": 237.26340230402684, "count": 9505, "is_parallel": true, "self": 237.26340230402684 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11839824100024998, "count": 1, "self": 0.0008372170004804502, "children": { "RLTrainer._checkpoint": { "total": 0.11756102399976953, "count": 1, "self": 0.11756102399976953 } } } } } } }