{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.030167818069458, "min": 1.030167818069458, "max": 2.854628562927246, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9824.7099609375, "min": 9824.7099609375, "max": 29234.25, "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": 11.656730651855469, "min": 0.337136834859848, "max": 11.656730651855469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2273.0625, "min": 65.40454864501953, "max": 2331.93115234375, "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": 0.07860325929062788, "min": 0.06419328652977414, "max": 0.079023222049442, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3144130371625115, "min": 0.2732737117539281, "max": 0.3758670120885511, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19407042335061467, "min": 0.10347782381737203, "max": 0.29161791824827005, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7762816934024587, "min": 0.4139112952694881, "max": 1.4580895912413503, "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": 23.454545454545453, "min": 3.0681818181818183, "max": 23.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1032.0, "min": 135.0, "max": 1247.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.454545454545453, "min": 3.0681818181818183, "max": 23.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1032.0, "min": 135.0, "max": 1247.0, "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": "1674131528", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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", "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": "1674131957" }, "total": 429.045754347, "count": 1, "self": 0.39251858300002596, "children": { "run_training.setup": { "total": 0.10729845399998794, "count": 1, "self": 0.10729845399998794 }, "TrainerController.start_learning": { "total": 428.54593731, "count": 1, "self": 0.5139913600005457, "children": { "TrainerController._reset_env": { "total": 9.032997671999993, "count": 1, "self": 9.032997671999993 }, "TrainerController.advance": { "total": 418.87340346399947, "count": 18200, "self": 0.27177370198762674, "children": { "env_step": { "total": 418.60162976201184, "count": 18200, "self": 273.96874686401327, "children": { "SubprocessEnvManager._take_step": { "total": 144.37730195500467, "count": 18200, "self": 1.3693572290106317, "children": { "TorchPolicy.evaluate": { "total": 143.00794472599404, "count": 18200, "self": 30.792884337993627, "children": { "TorchPolicy.sample_actions": { "total": 112.21506038800041, "count": 18200, "self": 112.21506038800041 } } } } }, "workers": { "total": 0.2555809429939302, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 427.3645493800006, "count": 18200, "is_parallel": true, "self": 206.4111205170052, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053927840000085325, "count": 1, "is_parallel": true, "self": 0.003075023999969062, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023177600000394705, "count": 10, "is_parallel": true, "self": 0.0023177600000394705 } } }, "UnityEnvironment.step": { "total": 0.04479632999999694, "count": 1, "is_parallel": true, "self": 0.0005279079999809255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032089000001178647, "count": 1, "is_parallel": true, "self": 0.00032089000001178647 }, "communicator.exchange": { "total": 0.042294696999988446, "count": 1, "is_parallel": true, "self": 0.042294696999988446 }, "steps_from_proto": { "total": 0.0016528350000157843, "count": 1, "is_parallel": true, "self": 0.0004175839999902564, "children": { "_process_rank_one_or_two_observation": { "total": 0.001235251000025528, "count": 10, "is_parallel": true, "self": 0.001235251000025528 } } } } } } }, "UnityEnvironment.step": { "total": 220.9534288629954, "count": 18199, "is_parallel": true, "self": 8.360477121978874, "children": { "UnityEnvironment._generate_step_input": { "total": 4.971923549012274, "count": 18199, "is_parallel": true, "self": 4.971923549012274 }, "communicator.exchange": { "total": 177.21207474900342, "count": 18199, "is_parallel": true, "self": 177.21207474900342 }, "steps_from_proto": { "total": 30.408953443000826, "count": 18199, "is_parallel": true, "self": 6.556399549012838, "children": { "_process_rank_one_or_two_observation": { "total": 23.852553893987988, "count": 181990, "is_parallel": true, "self": 23.852553893987988 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.71779999568389e-05, "count": 1, "self": 3.71779999568389e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 415.9336498150303, "count": 336885, "is_parallel": true, "self": 8.96063994401095, "children": { "process_trajectory": { "total": 239.20879032801955, "count": 336885, "is_parallel": true, "self": 238.53025636801962, "children": { "RLTrainer._checkpoint": { "total": 0.6785339599999247, "count": 4, "is_parallel": true, "self": 0.6785339599999247 } } }, "_update_policy": { "total": 167.7642195429998, "count": 90, "is_parallel": true, "self": 42.72112703999932, "children": { "TorchPPOOptimizer.update": { "total": 125.04309250300048, "count": 4587, "is_parallel": true, "self": 125.04309250300048 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12550763600006576, "count": 1, "self": 0.0009184630000618199, "children": { "RLTrainer._checkpoint": { "total": 0.12458917300000394, "count": 1, "self": 0.12458917300000394 } } } } } } }