{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8677033185958862, "min": 0.8677033185958862, "max": 2.8615362644195557, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8246.65234375, "min": 8246.65234375, "max": 29210.5625, "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": 12.944300651550293, "min": 0.3074929416179657, "max": 12.944300651550293, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2524.138671875, "min": 59.65363311767578, "max": 2619.086181640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06317977850170899, "min": 0.06009784874970815, "max": 0.07279667381320479, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25271911400683594, "min": 0.2403913949988326, "max": 0.3639833690660239, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19806585964911125, "min": 0.1087355299934964, "max": 0.2824960858214135, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.792263438596445, "min": 0.4349421199739856, "max": 1.4124804291070676, "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.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.Environment.CumulativeReward.mean": { "value": 26.204545454545453, "min": 3.1818181818181817, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1153.0, "min": 140.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.204545454545453, "min": 3.1818181818181817, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1153.0, "min": 140.0, "max": 1399.0, "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": "1754459969", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754460398" }, "total": 429.19280162199993, "count": 1, "self": 0.5308871870001894, "children": { "run_training.setup": { "total": 0.030572421999750077, "count": 1, "self": 0.030572421999750077 }, "TrainerController.start_learning": { "total": 428.631342013, "count": 1, "self": 0.3385535030056417, "children": { "TrainerController._reset_env": { "total": 3.790949320999971, "count": 1, "self": 3.790949320999971 }, "TrainerController.advance": { "total": 424.38459938499454, "count": 18192, "self": 0.3716042129435664, "children": { "env_step": { "total": 305.0251319490435, "count": 18192, "self": 233.81970843821182, "children": { "SubprocessEnvManager._take_step": { "total": 70.99580778291056, "count": 18192, "self": 1.270948079882146, "children": { "TorchPolicy.evaluate": { "total": 69.72485970302841, "count": 18192, "self": 69.72485970302841 } } }, "workers": { "total": 0.20961572792111838, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 427.1802603070055, "count": 18192, "is_parallel": true, "self": 221.94359290501325, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005315182000231289, "count": 1, "is_parallel": true, "self": 0.003827870000350231, "children": { "_process_rank_one_or_two_observation": { "total": 0.001487311999881058, "count": 10, "is_parallel": true, "self": 0.001487311999881058 } } }, "UnityEnvironment.step": { "total": 0.042338492999988375, "count": 1, "is_parallel": true, "self": 0.0006842880002295715, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007279129995367839, "count": 1, "is_parallel": true, "self": 0.0007279129995367839 }, "communicator.exchange": { "total": 0.03859571100019821, "count": 1, "is_parallel": true, "self": 0.03859571100019821 }, "steps_from_proto": { "total": 0.0023305810000238125, "count": 1, "is_parallel": true, "self": 0.000414120998357248, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019164600016665645, "count": 10, "is_parallel": true, "self": 0.0019164600016665645 } } } } } } }, "UnityEnvironment.step": { "total": 205.23666740199224, "count": 18191, "is_parallel": true, "self": 9.907402479967459, "children": { "UnityEnvironment._generate_step_input": { "total": 5.485002675008218, "count": 18191, "is_parallel": true, "self": 5.485002675008218 }, "communicator.exchange": { "total": 157.22555530501904, "count": 18191, "is_parallel": true, "self": 157.22555530501904 }, "steps_from_proto": { "total": 32.618706941997516, "count": 18191, "is_parallel": true, "self": 5.790055114850475, "children": { "_process_rank_one_or_two_observation": { "total": 26.82865182714704, "count": 181910, "is_parallel": true, "self": 26.82865182714704 } } } } } } } } } } }, "trainer_advance": { "total": 118.98786322300748, "count": 18192, "self": 0.40026421710081195, "children": { "process_trajectory": { "total": 26.596207322904775, "count": 18192, "self": 26.187804521903672, "children": { "RLTrainer._checkpoint": { "total": 0.4084028010011025, "count": 4, "self": 0.4084028010011025 } } }, "_update_policy": { "total": 91.9913916830019, "count": 90, "self": 37.608673527037354, "children": { "TorchPPOOptimizer.update": { "total": 54.38271815596454, "count": 4587, "self": 54.38271815596454 } } } } } } }, "trainer_threads": { "total": 1.0109997674589977e-06, "count": 1, "self": 1.0109997674589977e-06 }, "TrainerController._save_models": { "total": 0.11723879300006956, "count": 1, "self": 0.0008521689996996429, "children": { "RLTrainer._checkpoint": { "total": 0.11638662400036992, "count": 1, "self": 0.11638662400036992 } } } } } } }