{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.7754155397415161, "min": 1.7754155397415161, "max": 2.8685004711151123, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 18221.08984375, "min": 17726.8515625, "max": 29439.419921875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.058207511901855, "min": 0.33712783455848694, "max": 8.058207511901855, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1643.874267578125, "min": 65.40280151367188, "max": 1643.874267578125, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06453465244800706, "min": 0.05985766598671177, "max": 0.0732384759267363, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3226732622400353, "min": 0.2394306639468471, "max": 0.35417465852829166, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2746957413121766, "min": 0.10077554168289199, "max": 0.32020172593640345, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.3734787065608831, "min": 0.40310216673156796, "max": 1.3734787065608831, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.327272727272728, "min": 3.0454545454545454, "max": 17.327272727272728, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 953.0, "min": 134.0, "max": 953.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.327272727272728, "min": 3.0454545454545454, "max": 17.327272727272728, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 953.0, "min": 134.0, "max": 953.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680681760", "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": "1680682018" }, "total": 258.02262799899995, "count": 1, "self": 0.5966422189999321, "children": { "run_training.setup": { "total": 0.11829940500001612, "count": 1, "self": 0.11829940500001612 }, "TrainerController.start_learning": { "total": 257.307686375, "count": 1, "self": 0.34107767900229646, "children": { "TrainerController._reset_env": { "total": 3.8544526220000535, "count": 1, "self": 3.8544526220000535 }, "TrainerController.advance": { "total": 252.94368964599778, "count": 9135, "self": 0.16660954700239472, "children": { "env_step": { "total": 252.77708009899538, "count": 9135, "self": 183.78151329101047, "children": { "SubprocessEnvManager._take_step": { "total": 68.83853216099772, "count": 9135, "self": 0.9457123219990535, "children": { "TorchPolicy.evaluate": { "total": 67.89281983899866, "count": 9135, "self": 67.89281983899866 } } }, "workers": { "total": 0.15703464698719927, "count": 9135, "self": 0.0, "children": { "worker_root": { "total": 256.29790659399896, "count": 9135, "is_parallel": true, "self": 118.9342820780007, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005387194000036288, "count": 1, "is_parallel": true, "self": 0.0036750579998852118, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017121360001510766, "count": 10, "is_parallel": true, "self": 0.0017121360001510766 } } }, "UnityEnvironment.step": { "total": 0.037792648999925404, "count": 1, "is_parallel": true, "self": 0.00041775499983032205, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003637300000036703, "count": 1, "is_parallel": true, "self": 0.0003637300000036703 }, "communicator.exchange": { "total": 0.035764680000056615, "count": 1, "is_parallel": true, "self": 0.035764680000056615 }, "steps_from_proto": { "total": 0.0012464840000347976, "count": 1, "is_parallel": true, "self": 0.00027219799983413395, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009742860002006637, "count": 10, "is_parallel": true, "self": 0.0009742860002006637 } } } } } } }, "UnityEnvironment.step": { "total": 137.36362451599825, "count": 9134, "is_parallel": true, "self": 5.583341717987992, "children": { "UnityEnvironment._generate_step_input": { "total": 3.146836990005113, "count": 9134, "is_parallel": true, "self": 3.146836990005113 }, "communicator.exchange": { "total": 109.82320802800098, "count": 9134, "is_parallel": true, "self": 109.82320802800098 }, "steps_from_proto": { "total": 18.810237780004172, "count": 9134, "is_parallel": true, "self": 3.872548089011616, "children": { "_process_rank_one_or_two_observation": { "total": 14.937689690992556, "count": 91340, "is_parallel": true, "self": 14.937689690992556 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00039006199995128554, "count": 1, "self": 0.00039006199995128554, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 250.76557696301506, "count": 231046, "is_parallel": true, "self": 6.168435413013981, "children": { "process_trajectory": { "total": 140.3849589320008, "count": 231046, "is_parallel": true, "self": 139.94762096300076, "children": { "RLTrainer._checkpoint": { "total": 0.4373379690000547, "count": 2, "is_parallel": true, "self": 0.4373379690000547 } } }, "_update_policy": { "total": 104.21218261800027, "count": 45, "is_parallel": true, "self": 38.24798744499651, "children": { "TorchPPOOptimizer.update": { "total": 65.96419517300376, "count": 2292, "is_parallel": true, "self": 65.96419517300376 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16807636599992293, "count": 1, "self": 0.0009080169999151622, "children": { "RLTrainer._checkpoint": { "total": 0.16716834900000777, "count": 1, "self": 0.16716834900000777 } } } } } } }