{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5981085300445557, "min": 0.5391741991043091, "max": 2.860793113708496, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6092.33349609375, "min": 5325.962890625, "max": 29234.4453125, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9984.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9984.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.3221491575241089, "min": 0.1301867663860321, "max": 1.3638598918914795, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 457.463623046875, "min": 44.914432525634766, "max": 482.806396484375, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07016996156045364, "min": 0.06052326545114721, "max": 0.07416873541089944, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2806798462418146, "min": 0.24209306180458884, "max": 0.37084367705449717, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.08974823132887776, "min": 0.04214331837126748, "max": 0.1073659083933807, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.358992925315511, "min": 0.16857327348506992, "max": 0.536300304619705, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.891098702999994e-06, "min": 3.891098702999994e-06, "max": 0.000295941001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5564394811999976e-05, "min": 1.5564394811999976e-05, "max": 0.0014425800191399996, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101297, "min": 0.101297, "max": 0.19864700000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405188, "min": 0.405188, "max": 0.98086, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999992e-05, "min": 7.472029999999992e-05, "max": 0.004932485299999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999966, "min": 0.00029888119999999966, "max": 0.024044914, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.59090909090909, "min": 3.409090909090909, "max": 26.618181818181817, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 150.0, "max": 1464.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.409090909090909, "max": 26.618181818181817, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 150.0, "max": 1464.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708890849", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708891754" }, "total": 904.4037863440001, "count": 1, "self": 0.431916124999816, "children": { "run_training.setup": { "total": 0.06732505400009359, "count": 1, "self": 0.06732505400009359 }, "TrainerController.start_learning": { "total": 903.9045451650002, "count": 1, "self": 1.1012265189965547, "children": { "TrainerController._reset_env": { "total": 3.9492779869999595, "count": 1, "self": 3.9492779869999595 }, "TrainerController.advance": { "total": 898.7449860340034, "count": 36394, "self": 0.5108845409631613, "children": { "env_step": { "total": 898.2341014930403, "count": 36394, "self": 618.1659180380441, "children": { "SubprocessEnvManager._take_step": { "total": 279.4029034069756, "count": 36394, "self": 2.8841890079729637, "children": { "TorchPolicy.evaluate": { "total": 276.51871439900265, "count": 36394, "self": 276.51871439900265 } } }, "workers": { "total": 0.6652800480205769, "count": 36394, "self": 0.0, "children": { "worker_root": { "total": 901.7066018290195, "count": 36394, "is_parallel": true, "self": 467.34425893099524, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005935360999956174, "count": 1, "is_parallel": true, "self": 0.004240405999553332, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016949550004028424, "count": 10, "is_parallel": true, "self": 0.0016949550004028424 } } }, "UnityEnvironment.step": { "total": 0.03477564400009214, "count": 1, "is_parallel": true, "self": 0.0006054920002043218, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041499300004943507, "count": 1, "is_parallel": true, "self": 0.00041499300004943507 }, "communicator.exchange": { "total": 0.031824534999941534, "count": 1, "is_parallel": true, "self": 0.031824534999941534 }, "steps_from_proto": { "total": 0.0019306239998968522, "count": 1, "is_parallel": true, "self": 0.00037683899972762447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015537850001692277, "count": 10, "is_parallel": true, "self": 0.0015537850001692277 } } } } } } }, "UnityEnvironment.step": { "total": 434.3623428980243, "count": 36393, "is_parallel": true, "self": 20.91000053103471, "children": { "UnityEnvironment._generate_step_input": { "total": 10.735746653987462, "count": 36393, "is_parallel": true, "self": 10.735746653987462 }, "communicator.exchange": { "total": 336.2750735679849, "count": 36393, "is_parallel": true, "self": 336.2750735679849 }, "steps_from_proto": { "total": 66.44152214501719, "count": 36393, "is_parallel": true, "self": 12.178073454851756, "children": { "_process_rank_one_or_two_observation": { "total": 54.26344869016543, "count": 363930, "is_parallel": true, "self": 54.26344869016543 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002337320001970511, "count": 1, "self": 0.0002337320001970511, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 886.1473836219657, "count": 1492859, "is_parallel": true, "self": 31.63233189491484, "children": { "process_trajectory": { "total": 575.924164254054, "count": 1492859, "is_parallel": true, "self": 574.6473926670542, "children": { "RLTrainer._checkpoint": { "total": 1.2767715869997573, "count": 8, "is_parallel": true, "self": 1.2767715869997573 } } }, "_update_policy": { "total": 278.5908874729969, "count": 181, "is_parallel": true, "self": 95.8887579720199, "children": { "TorchPPOOptimizer.update": { "total": 182.70212950097698, "count": 9228, "is_parallel": true, "self": 182.70212950097698 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10882089300002917, "count": 1, "self": 0.001161881999905745, "children": { "RLTrainer._checkpoint": { "total": 0.10765901100012343, "count": 1, "self": 0.10765901100012343 } } } } } } }