{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0842323303222656, "min": 1.0842323303222656, "max": 2.861264705657959, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10399.95703125, "min": 10399.95703125, "max": 29302.2109375, "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": 12.575250625610352, "min": 0.11546643078327179, "max": 12.575250625610352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2452.173828125, "min": 22.400487899780273, "max": 2544.47607421875, "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": 0.07169622975697185, "min": 0.06073294943501013, "max": 0.0732895495589165, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2867849190278874, "min": 0.25330409842764295, "max": 0.36644774779458256, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2271452642538968, "min": 0.12217832938539705, "max": 0.27457926781738506, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9085810570155872, "min": 0.4887133175415882, "max": 1.3728963390869253, "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": 24.65909090909091, "min": 2.909090909090909, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1085.0, "min": 128.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.65909090909091, "min": 2.909090909090909, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1085.0, "min": 128.0, "max": 1360.0, "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": "1723576860", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723577327" }, "total": 467.20624824500004, "count": 1, "self": 0.5864222300000961, "children": { "run_training.setup": { "total": 0.06450649799995745, "count": 1, "self": 0.06450649799995745 }, "TrainerController.start_learning": { "total": 466.555319517, "count": 1, "self": 0.6653794629968388, "children": { "TrainerController._reset_env": { "total": 3.099456148999991, "count": 1, "self": 3.099456148999991 }, "TrainerController.advance": { "total": 462.64781827500303, "count": 18221, "self": 0.31501958001086905, "children": { "env_step": { "total": 462.33279869499216, "count": 18221, "self": 302.99246263399647, "children": { "SubprocessEnvManager._take_step": { "total": 159.0059718560031, "count": 18221, "self": 1.555690205006158, "children": { "TorchPolicy.evaluate": { "total": 157.45028165099694, "count": 18221, "self": 157.45028165099694 } } }, "workers": { "total": 0.3343642049925961, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 465.19173184699923, "count": 18221, "is_parallel": true, "self": 232.3087718799946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008340730000043095, "count": 1, "is_parallel": true, "self": 0.006615839000005508, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017248910000375872, "count": 10, "is_parallel": true, "self": 0.0017248910000375872 } } }, "UnityEnvironment.step": { "total": 0.08730285299998286, "count": 1, "is_parallel": true, "self": 0.0007961219999401692, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004853369999864299, "count": 1, "is_parallel": true, "self": 0.0004853369999864299 }, "communicator.exchange": { "total": 0.07688951900001939, "count": 1, "is_parallel": true, "self": 0.07688951900001939 }, "steps_from_proto": { "total": 0.009131875000036871, "count": 1, "is_parallel": true, "self": 0.007573320000062722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015585549999741488, "count": 10, "is_parallel": true, "self": 0.0015585549999741488 } } } } } } }, "UnityEnvironment.step": { "total": 232.88295996700464, "count": 18220, "is_parallel": true, "self": 10.532593353000891, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4429574090042365, "count": 18220, "is_parallel": true, "self": 5.4429574090042365 }, "communicator.exchange": { "total": 182.91158742199684, "count": 18220, "is_parallel": true, "self": 182.91158742199684 }, "steps_from_proto": { "total": 33.99582178300267, "count": 18220, "is_parallel": true, "self": 6.589769934027572, "children": { "_process_rank_one_or_two_observation": { "total": 27.406051848975096, "count": 182200, "is_parallel": true, "self": 27.406051848975096 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001737910000656484, "count": 1, "self": 0.0001737910000656484, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.2344795390123, "count": 703527, "is_parallel": true, "self": 14.321536867013094, "children": { "process_trajectory": { "total": 254.7714479469991, "count": 703527, "is_parallel": true, "self": 253.65548274799903, "children": { "RLTrainer._checkpoint": { "total": 1.1159651990000725, "count": 4, "is_parallel": true, "self": 1.1159651990000725 } } }, "_update_policy": { "total": 188.1414947250001, "count": 90, "is_parallel": true, "self": 58.0929464800011, "children": { "TorchPPOOptimizer.update": { "total": 130.04854824499898, "count": 4587, "is_parallel": true, "self": 130.04854824499898 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14249183900005846, "count": 1, "self": 0.0012529300000778676, "children": { "RLTrainer._checkpoint": { "total": 0.1412389089999806, "count": 1, "self": 0.1412389089999806 } } } } } } }