{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0243574380874634, "min": 1.0243574380874634, "max": 2.8514244556427, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9791.8330078125, "min": 9791.8330078125, "max": 29201.4375, "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": 12.594819068908691, "min": 0.2126627117395401, "max": 12.594819068908691, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2455.98974609375, "min": 41.25656509399414, "max": 2546.0478515625, "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": 0.06976543032471776, "min": 0.06373715597474788, "max": 0.07900001253138351, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.279061721298871, "min": 0.25494862389899153, "max": 0.3662598628508539, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2090673302756805, "min": 0.10179276747615351, "max": 0.28692926159676385, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.836269321102722, "min": 0.40717106990461405, "max": 1.3954119606345308, "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": 25.25, "min": 2.772727272727273, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 122.0, "max": 1348.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 2.772727272727273, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 122.0, "max": 1348.0, "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": "1678987888", "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": "1678988351" }, "total": 463.3101122810001, "count": 1, "self": 0.43828742800019427, "children": { "run_training.setup": { "total": 0.10629578799989758, "count": 1, "self": 0.10629578799989758 }, "TrainerController.start_learning": { "total": 462.765529065, "count": 1, "self": 0.5593381740197856, "children": { "TrainerController._reset_env": { "total": 8.878504322000026, "count": 1, "self": 8.878504322000026 }, "TrainerController.advance": { "total": 453.1906624839801, "count": 18202, "self": 0.2815996359881865, "children": { "env_step": { "total": 452.9090628479919, "count": 18202, "self": 327.09052019202113, "children": { "SubprocessEnvManager._take_step": { "total": 125.54852282400384, "count": 18202, "self": 2.1428186050136446, "children": { "TorchPolicy.evaluate": { "total": 123.4057042189902, "count": 18202, "self": 123.4057042189902 } } }, "workers": { "total": 0.2700198319669198, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 461.2331050080161, "count": 18202, "is_parallel": true, "self": 218.7150875520017, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005987263999941206, "count": 1, "is_parallel": true, "self": 0.004534245000058945, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014530189998822607, "count": 10, "is_parallel": true, "self": 0.0014530189998822607 } } }, "UnityEnvironment.step": { "total": 0.03569756199999574, "count": 1, "is_parallel": true, "self": 0.0006034919999819977, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038060299993958324, "count": 1, "is_parallel": true, "self": 0.00038060299993958324 }, "communicator.exchange": { "total": 0.0327463630001148, "count": 1, "is_parallel": true, "self": 0.0327463630001148 }, "steps_from_proto": { "total": 0.001967103999959363, "count": 1, "is_parallel": true, "self": 0.00041903700002876576, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015480669999305974, "count": 10, "is_parallel": true, "self": 0.0015480669999305974 } } } } } } }, "UnityEnvironment.step": { "total": 242.51801745601438, "count": 18201, "is_parallel": true, "self": 9.432644132044288, "children": { "UnityEnvironment._generate_step_input": { "total": 5.045818154995459, "count": 18201, "is_parallel": true, "self": 5.045818154995459 }, "communicator.exchange": { "total": 197.2696501019684, "count": 18201, "is_parallel": true, "self": 197.2696501019684 }, "steps_from_proto": { "total": 30.76990506700622, "count": 18201, "is_parallel": true, "self": 6.052496116051316, "children": { "_process_rank_one_or_two_observation": { "total": 24.717408950954905, "count": 182010, "is_parallel": true, "self": 24.717408950954905 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001504740000655147, "count": 1, "self": 0.0001504740000655147, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 449.85755961290624, "count": 409948, "is_parallel": true, "self": 9.656328460796203, "children": { "process_trajectory": { "total": 251.26450734711102, "count": 409948, "is_parallel": true, "self": 250.357699333111, "children": { "RLTrainer._checkpoint": { "total": 0.9068080140000347, "count": 4, "is_parallel": true, "self": 0.9068080140000347 } } }, "_update_policy": { "total": 188.93672380499902, "count": 90, "is_parallel": true, "self": 69.67861518300288, "children": { "TorchPPOOptimizer.update": { "total": 119.25810862199614, "count": 4587, "is_parallel": true, "self": 119.25810862199614 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13687361100005546, "count": 1, "self": 0.00098592200015446, "children": { "RLTrainer._checkpoint": { "total": 0.135887688999901, "count": 1, "self": 0.135887688999901 } } } } } } }