{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0569307804107666, "min": 1.0569307804107666, "max": 2.8642020225524902, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10103.201171875, "min": 10103.201171875, "max": 29426.8125, "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": 13.20996379852295, "min": 0.26008087396621704, "max": 13.20996379852295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2575.94287109375, "min": 50.4556884765625, "max": 2677.20849609375, "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": 0.07125938101571769, "min": 0.06259548788680239, "max": 0.0727421351492761, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28503752406287075, "min": 0.2677971020103524, "max": 0.34895936624539614, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19193527097905091, "min": 0.1181693082896755, "max": 0.30353191150169745, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7677410839162037, "min": 0.472677233158702, "max": 1.5176595575084872, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.3510097298000007e-05, "min": 1.3510097298000007e-05, "max": 0.00048647000270600005, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.404038919200003e-05, "min": 5.404038919200003e-05, "max": 0.00230860003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10270200000000002, "min": 0.10270200000000002, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41080800000000006, "min": 0.41080800000000006, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001448298000000001, "min": 0.0001448298000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005793192000000004, "min": 0.0005793192000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.727272727272727, "min": 3.0, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 132.0, "max": 1445.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.0, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 132.0, "max": 1445.0, "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": "1681378931", "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": "1681379391" }, "total": 460.081802132, "count": 1, "self": 0.4796732279999105, "children": { "run_training.setup": { "total": 0.16620986399993853, "count": 1, "self": 0.16620986399993853 }, "TrainerController.start_learning": { "total": 459.43591904000016, "count": 1, "self": 0.7098543060050133, "children": { "TrainerController._reset_env": { "total": 0.8126556419999815, "count": 1, "self": 0.8126556419999815 }, "TrainerController.advance": { "total": 457.7465526509952, "count": 18210, "self": 0.3605461599810269, "children": { "env_step": { "total": 457.3860064910142, "count": 18210, "self": 371.2353144550285, "children": { "SubprocessEnvManager._take_step": { "total": 85.78835190099699, "count": 18210, "self": 2.069298845994581, "children": { "TorchPolicy.evaluate": { "total": 83.7190530550024, "count": 18210, "self": 83.7190530550024 } } }, "workers": { "total": 0.362340134988699, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 457.68400684498704, "count": 18210, "is_parallel": true, "self": 203.44789659797652, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005813698999986627, "count": 1, "is_parallel": true, "self": 0.004091928999969241, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017217700000173863, "count": 10, "is_parallel": true, "self": 0.0017217700000173863 } } }, "UnityEnvironment.step": { "total": 0.04434522300005028, "count": 1, "is_parallel": true, "self": 0.0038233790000958834, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004709999999477077, "count": 1, "is_parallel": true, "self": 0.0004709999999477077 }, "communicator.exchange": { "total": 0.038162473999932445, "count": 1, "is_parallel": true, "self": 0.038162473999932445 }, "steps_from_proto": { "total": 0.0018883700000742465, "count": 1, "is_parallel": true, "self": 0.00040114000000812666, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014872300000661198, "count": 10, "is_parallel": true, "self": 0.0014872300000661198 } } } } } } }, "UnityEnvironment.step": { "total": 254.23611024701052, "count": 18209, "is_parallel": true, "self": 10.526985229014372, "children": { "UnityEnvironment._generate_step_input": { "total": 6.229981040991333, "count": 18209, "is_parallel": true, "self": 6.229981040991333 }, "communicator.exchange": { "total": 205.82622670000387, "count": 18209, "is_parallel": true, "self": 205.82622670000387 }, "steps_from_proto": { "total": 31.652917277000938, "count": 18209, "is_parallel": true, "self": 6.396088683057201, "children": { "_process_rank_one_or_two_observation": { "total": 25.256828593943737, "count": 182090, "is_parallel": true, "self": 25.256828593943737 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016221100008806388, "count": 1, "self": 0.00016221100008806388, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.1733207599858, "count": 474742, "is_parallel": true, "self": 10.610699662037177, "children": { "process_trajectory": { "total": 249.2538576929487, "count": 474742, "is_parallel": true, "self": 248.15016657094873, "children": { "RLTrainer._checkpoint": { "total": 1.1036911219999865, "count": 4, "is_parallel": true, "self": 1.1036911219999865 } } }, "_update_policy": { "total": 194.30876340499992, "count": 90, "is_parallel": true, "self": 54.799155232999624, "children": { "TorchPPOOptimizer.update": { "total": 139.5096081720003, "count": 4584, "is_parallel": true, "self": 139.5096081720003 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16669422999984818, "count": 1, "self": 0.0010501489998659963, "children": { "RLTrainer._checkpoint": { "total": 0.16564408099998218, "count": 1, "self": 0.16564408099998218 } } } } } } }