{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9645525813102722, "min": 0.9645525813102722, "max": 2.847583293914795, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9220.158203125, "min": 9220.158203125, "max": 29162.1015625, "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": 12.606156349182129, "min": 0.3813416063785553, "max": 12.606156349182129, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2458.200439453125, "min": 73.98027038574219, "max": 2540.14453125, "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": 0.07113316300785978, "min": 0.06093346953104414, "max": 0.07191983017997414, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2845326520314391, "min": 0.24373387812417657, "max": 0.3595991508998707, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2480439863660756, "min": 0.1282997032234847, "max": 0.25423773363524793, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9921759454643024, "min": 0.5131988128939388, "max": 1.2711886681762397, "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": 25.045454545454547, "min": 3.8181818181818183, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 168.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 3.8181818181818183, "max": 25.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 168.0, "max": 1375.0, "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": "1683998558", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683999029" }, "total": 470.9744404720001, "count": 1, "self": 0.7331072500002165, "children": { "run_training.setup": { "total": 0.06701694999992469, "count": 1, "self": 0.06701694999992469 }, "TrainerController.start_learning": { "total": 470.17431627199994, "count": 1, "self": 0.612444432006555, "children": { "TrainerController._reset_env": { "total": 4.40208901799997, "count": 1, "self": 4.40208901799997 }, "TrainerController.advance": { "total": 464.9361176609931, "count": 18204, "self": 0.3080657869893457, "children": { "env_step": { "total": 464.62805187400375, "count": 18204, "self": 339.3596827910121, "children": { "SubprocessEnvManager._take_step": { "total": 124.97573235901018, "count": 18204, "self": 1.9438709179910347, "children": { "TorchPolicy.evaluate": { "total": 123.03186144101915, "count": 18204, "self": 123.03186144101915 } } }, "workers": { "total": 0.29263672398144536, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 468.4612479799913, "count": 18204, "is_parallel": true, "self": 218.22129838298906, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005725771000015811, "count": 1, "is_parallel": true, "self": 0.0033543520000876015, "children": { "_process_rank_one_or_two_observation": { "total": 0.00237141899992821, "count": 10, "is_parallel": true, "self": 0.00237141899992821 } } }, "UnityEnvironment.step": { "total": 0.04123971399997117, "count": 1, "is_parallel": true, "self": 0.0006946040000457288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004057989999637357, "count": 1, "is_parallel": true, "self": 0.0004057989999637357 }, "communicator.exchange": { "total": 0.03777606599999217, "count": 1, "is_parallel": true, "self": 0.03777606599999217 }, "steps_from_proto": { "total": 0.002363244999969538, "count": 1, "is_parallel": true, "self": 0.00042377900001611124, "children": { "_process_rank_one_or_two_observation": { "total": 0.001939465999953427, "count": 10, "is_parallel": true, "self": 0.001939465999953427 } } } } } } }, "UnityEnvironment.step": { "total": 250.23994959700224, "count": 18203, "is_parallel": true, "self": 9.603577765021669, "children": { "UnityEnvironment._generate_step_input": { "total": 5.338741713994864, "count": 18203, "is_parallel": true, "self": 5.338741713994864 }, "communicator.exchange": { "total": 202.17703508600573, "count": 18203, "is_parallel": true, "self": 202.17703508600573 }, "steps_from_proto": { "total": 33.120595031979974, "count": 18203, "is_parallel": true, "self": 6.502141618964515, "children": { "_process_rank_one_or_two_observation": { "total": 26.61845341301546, "count": 182030, "is_parallel": true, "self": 26.61845341301546 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012030200014123693, "count": 1, "self": 0.00012030200014123693, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.4260475869361, "count": 447673, "is_parallel": true, "self": 9.681764038955635, "children": { "process_trajectory": { "total": 249.97028775298043, "count": 447673, "is_parallel": true, "self": 248.7500579409807, "children": { "RLTrainer._checkpoint": { "total": 1.2202298119997295, "count": 4, "is_parallel": true, "self": 1.2202298119997295 } } }, "_update_policy": { "total": 201.77399579500002, "count": 90, "is_parallel": true, "self": 77.62871430999178, "children": { "TorchPPOOptimizer.update": { "total": 124.14528148500824, "count": 4584, "is_parallel": true, "self": 124.14528148500824 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22354485900018517, "count": 1, "self": 0.004783373000236679, "children": { "RLTrainer._checkpoint": { "total": 0.2187614859999485, "count": 1, "self": 0.2187614859999485 } } } } } } }