{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8908975720405579, "min": 0.8908975720405579, "max": 2.8596441745758057, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8516.08984375, "min": 8516.08984375, "max": 29285.6171875, "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": 12.80385971069336, "min": 0.30010712146759033, "max": 12.80385971069336, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2496.752685546875, "min": 58.22077941894531, "max": 2615.728515625, "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": 0.06850057131041289, "min": 0.06175059236790962, "max": 0.07279905359838248, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27400228524165154, "min": 0.25793274852356474, "max": 0.356982646625279, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19376820932124175, "min": 0.11176550857649714, "max": 0.2910649191515119, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.775072837284967, "min": 0.44706203430598856, "max": 1.4553245957575593, "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": 25.363636363636363, "min": 3.3636363636363638, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 148.0, "max": 1386.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.3636363636363638, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 148.0, "max": 1386.0, "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": "1678845643", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1678846124" }, "total": 481.843428636, "count": 1, "self": 0.43790650499988715, "children": { "run_training.setup": { "total": 0.10946153100007905, "count": 1, "self": 0.10946153100007905 }, "TrainerController.start_learning": { "total": 481.29606060000003, "count": 1, "self": 0.5546964220022801, "children": { "TrainerController._reset_env": { "total": 9.47220701699996, "count": 1, "self": 9.47220701699996 }, "TrainerController.advance": { "total": 471.11457825399793, "count": 18203, "self": 0.29026304800447633, "children": { "env_step": { "total": 470.82431520599346, "count": 18203, "self": 338.4604995519878, "children": { "SubprocessEnvManager._take_step": { "total": 132.07935626299934, "count": 18203, "self": 2.308585353009107, "children": { "TorchPolicy.evaluate": { "total": 129.77077090999023, "count": 18203, "self": 129.77077090999023 } } }, "workers": { "total": 0.284459391006294, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 479.74190566600566, "count": 18203, "is_parallel": true, "self": 231.15282636001257, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005595659000050546, "count": 1, "is_parallel": true, "self": 0.003982411000265529, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016132479997850169, "count": 10, "is_parallel": true, "self": 0.0016132479997850169 } } }, "UnityEnvironment.step": { "total": 0.09678969999993114, "count": 1, "is_parallel": true, "self": 0.0005726619999677496, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004187749999573498, "count": 1, "is_parallel": true, "self": 0.0004187749999573498 }, "communicator.exchange": { "total": 0.09392615199999454, "count": 1, "is_parallel": true, "self": 0.09392615199999454 }, "steps_from_proto": { "total": 0.0018721110000115004, "count": 1, "is_parallel": true, "self": 0.0004043879997652766, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014677230002462238, "count": 10, "is_parallel": true, "self": 0.0014677230002462238 } } } } } } }, "UnityEnvironment.step": { "total": 248.5890793059931, "count": 18202, "is_parallel": true, "self": 9.837849822961743, "children": { "UnityEnvironment._generate_step_input": { "total": 5.515275527020208, "count": 18202, "is_parallel": true, "self": 5.515275527020208 }, "communicator.exchange": { "total": 200.26811426700624, "count": 18202, "is_parallel": true, "self": 200.26811426700624 }, "steps_from_proto": { "total": 32.967839689004904, "count": 18202, "is_parallel": true, "self": 6.628047712993862, "children": { "_process_rank_one_or_two_observation": { "total": 26.339791976011043, "count": 182020, "is_parallel": true, "self": 26.339791976011043 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001298549998409726, "count": 1, "self": 0.0001298549998409726, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 467.396737977057, "count": 425848, "is_parallel": true, "self": 10.539504769094037, "children": { "process_trajectory": { "total": 259.9056872349653, "count": 425848, "is_parallel": true, "self": 259.1030968689653, "children": { "RLTrainer._checkpoint": { "total": 0.802590366000004, "count": 4, "is_parallel": true, "self": 0.802590366000004 } } }, "_update_policy": { "total": 196.95154597299768, "count": 90, "is_parallel": true, "self": 72.97190170400006, "children": { "TorchPPOOptimizer.update": { "total": 123.97964426899762, "count": 4587, "is_parallel": true, "self": 123.97964426899762 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15444905200001813, "count": 1, "self": 0.001003004000040164, "children": { "RLTrainer._checkpoint": { "total": 0.15344604799997796, "count": 1, "self": 0.15344604799997796 } } } } } } }