{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0924500226974487, "min": 1.0924500226974487, "max": 2.871011257171631, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10442.7294921875, "min": 10442.7294921875, "max": 29433.607421875, "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": 11.969993591308594, "min": 0.41508492827415466, "max": 11.969993591308594, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2334.148681640625, "min": 80.52647399902344, "max": 2377.607421875, "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": 0.06915072155813916, "min": 0.06360901765041418, "max": 0.07945232800648584, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27660288623255663, "min": 0.25443607060165674, "max": 0.3972616400324292, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20598531799281344, "min": 0.1303618755716575, "max": 0.2789942549621739, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8239412719712538, "min": 0.52144750228663, "max": 1.3453191404833513, "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": 24.272727272727273, "min": 3.590909090909091, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1068.0, "min": 158.0, "max": 1288.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.272727272727273, "min": 3.590909090909091, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1068.0, "min": 158.0, "max": 1288.0, "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": "1735217579", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735218191" }, "total": 611.137156926, "count": 1, "self": 0.54370644599976, "children": { "run_training.setup": { "total": 0.08339410700000371, "count": 1, "self": 0.08339410700000371 }, "TrainerController.start_learning": { "total": 610.5100563730002, "count": 1, "self": 0.9243355600674477, "children": { "TrainerController._reset_env": { "total": 8.263597371000287, "count": 1, "self": 8.263597371000287 }, "TrainerController.advance": { "total": 601.2343053449331, "count": 18202, "self": 0.43965686288765937, "children": { "env_step": { "total": 600.7946484820454, "count": 18202, "self": 457.89449106317215, "children": { "SubprocessEnvManager._take_step": { "total": 142.46761517491223, "count": 18202, "self": 2.6545951199113915, "children": { "TorchPolicy.evaluate": { "total": 139.81302005500083, "count": 18202, "self": 139.81302005500083 } } }, "workers": { "total": 0.432542243961052, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 608.633767935044, "count": 18202, "is_parallel": true, "self": 294.2518986990872, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008058956000240869, "count": 1, "is_parallel": true, "self": 0.005350487999749021, "children": { "_process_rank_one_or_two_observation": { "total": 0.002708468000491848, "count": 10, "is_parallel": true, "self": 0.002708468000491848 } } }, "UnityEnvironment.step": { "total": 0.04633580700010498, "count": 1, "is_parallel": true, "self": 0.0010587100000520877, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004977799999323906, "count": 1, "is_parallel": true, "self": 0.0004977799999323906 }, "communicator.exchange": { "total": 0.042038175000016054, "count": 1, "is_parallel": true, "self": 0.042038175000016054 }, "steps_from_proto": { "total": 0.002741142000104446, "count": 1, "is_parallel": true, "self": 0.0005249400001048343, "children": { "_process_rank_one_or_two_observation": { "total": 0.002216201999999612, "count": 10, "is_parallel": true, "self": 0.002216201999999612 } } } } } } }, "UnityEnvironment.step": { "total": 314.38186923595686, "count": 18201, "is_parallel": true, "self": 15.49595522489335, "children": { "UnityEnvironment._generate_step_input": { "total": 7.628161766124322, "count": 18201, "is_parallel": true, "self": 7.628161766124322 }, "communicator.exchange": { "total": 246.06817856895123, "count": 18201, "is_parallel": true, "self": 246.06817856895123 }, "steps_from_proto": { "total": 45.18957367598796, "count": 18201, "is_parallel": true, "self": 9.017220031999386, "children": { "_process_rank_one_or_two_observation": { "total": 36.17235364398857, "count": 182010, "is_parallel": true, "self": 36.17235364398857 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002049329996225424, "count": 1, "self": 0.0002049329996225424, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 593.9315898012565, "count": 783621, "is_parallel": true, "self": 18.28126973317694, "children": { "process_trajectory": { "total": 320.88957979507995, "count": 783621, "is_parallel": true, "self": 320.14646681307886, "children": { "RLTrainer._checkpoint": { "total": 0.7431129820010938, "count": 4, "is_parallel": true, "self": 0.7431129820010938 } } }, "_update_policy": { "total": 254.76074027299956, "count": 90, "is_parallel": true, "self": 71.8510801080065, "children": { "TorchPPOOptimizer.update": { "total": 182.90966016499306, "count": 4584, "is_parallel": true, "self": 182.90966016499306 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08761316399977659, "count": 1, "self": 0.0017287769996983116, "children": { "RLTrainer._checkpoint": { "total": 0.08588438700007828, "count": 1, "self": 0.08588438700007828 } } } } } } }