{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9019661545753479, "min": 0.9019661545753479, "max": 2.8619089126586914, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8611.97265625, "min": 8611.97265625, "max": 29308.80859375, "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": 12.927451133728027, "min": 0.3729897439479828, "max": 12.927451133728027, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.85302734375, "min": 72.3600082397461, "max": 2606.81396484375, "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": 0.07296858793672392, "min": 0.06369749667401445, "max": 0.07968366560507824, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2918743517468957, "min": 0.2569695268729108, "max": 0.35536560009167456, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20705967491456106, "min": 0.11972125027986133, "max": 0.2999466109801741, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8282386996582443, "min": 0.4788850011194453, "max": 1.397762338612594, "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": 25.613636363636363, "min": 3.25, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 143.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.25, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 143.0, "max": 1387.0, "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": "1676821899", "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": "1676822359" }, "total": 459.475447207, "count": 1, "self": 0.43857548599999063, "children": { "run_training.setup": { "total": 0.10901737699998648, "count": 1, "self": 0.10901737699998648 }, "TrainerController.start_learning": { "total": 458.927854344, "count": 1, "self": 0.5515299040098398, "children": { "TrainerController._reset_env": { "total": 10.306774573999974, "count": 1, "self": 10.306774573999974 }, "TrainerController.advance": { "total": 447.9500011359903, "count": 18202, "self": 0.3070536789779226, "children": { "env_step": { "total": 447.6429474570124, "count": 18202, "self": 308.02319883002815, "children": { "SubprocessEnvManager._take_step": { "total": 139.34350184199252, "count": 18202, "self": 1.4511868539725583, "children": { "TorchPolicy.evaluate": { "total": 137.89231498801996, "count": 18202, "self": 31.43288712500987, "children": { "TorchPolicy.sample_actions": { "total": 106.45942786301009, "count": 18202, "self": 106.45942786301009 } } } } }, "workers": { "total": 0.27624678499171296, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 457.1594237439872, "count": 18202, "is_parallel": true, "self": 220.09361814498618, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008089115000075253, "count": 1, "is_parallel": true, "self": 0.005510407999963718, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025787070001115353, "count": 10, "is_parallel": true, "self": 0.0025787070001115353 } } }, "UnityEnvironment.step": { "total": 0.0361173390000431, "count": 1, "is_parallel": true, "self": 0.00046449200010556524, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002550079999537047, "count": 1, "is_parallel": true, "self": 0.0002550079999537047 }, "communicator.exchange": { "total": 0.03372615000000678, "count": 1, "is_parallel": true, "self": 0.03372615000000678 }, "steps_from_proto": { "total": 0.0016716889999770501, "count": 1, "is_parallel": true, "self": 0.0004146590000573269, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012570299999197232, "count": 10, "is_parallel": true, "self": 0.0012570299999197232 } } } } } } }, "UnityEnvironment.step": { "total": 237.065805599001, "count": 18201, "is_parallel": true, "self": 9.67716410899709, "children": { "UnityEnvironment._generate_step_input": { "total": 5.16427118498973, "count": 18201, "is_parallel": true, "self": 5.16427118498973 }, "communicator.exchange": { "total": 191.1278694519932, "count": 18201, "is_parallel": true, "self": 191.1278694519932 }, "steps_from_proto": { "total": 31.096500853020984, "count": 18201, "is_parallel": true, "self": 6.827885567991871, "children": { "_process_rank_one_or_two_observation": { "total": 24.268615285029114, "count": 182010, "is_parallel": true, "self": 24.268615285029114 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015078699993864575, "count": 1, "self": 0.00015078699993864575, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.7305878208939, "count": 401037, "is_parallel": true, "self": 9.792230721940086, "children": { "process_trajectory": { "total": 254.09693897595355, "count": 401037, "is_parallel": true, "self": 253.40988956795366, "children": { "RLTrainer._checkpoint": { "total": 0.6870494079998934, "count": 4, "is_parallel": true, "self": 0.6870494079998934 } } }, "_update_policy": { "total": 180.84141812300027, "count": 90, "is_parallel": true, "self": 61.8810564350033, "children": { "TorchPPOOptimizer.update": { "total": 118.96036168799696, "count": 4587, "is_parallel": true, "self": 118.96036168799696 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1193979429999672, "count": 1, "self": 0.0008688039999924513, "children": { "RLTrainer._checkpoint": { "total": 0.11852913899997475, "count": 1, "self": 0.11852913899997475 } } } } } } }