{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9334244728088379, "min": 0.9233474135398865, "max": 2.8732075691223145, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8922.6044921875, "min": 8922.6044921875, "max": 29487.73046875, "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": 12.820881843566895, "min": 0.3518044352531433, "max": 12.820881843566895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2500.072021484375, "min": 68.25006103515625, "max": 2603.3291015625, "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": 0.0655991856805414, "min": 0.06183175187431391, "max": 0.07637537341489566, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2623967427221656, "min": 0.24732700749725564, "max": 0.37021538322904446, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20418837699381742, "min": 0.10869412846730878, "max": 0.2839040827809596, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8167535079752697, "min": 0.4347765138692351, "max": 1.3988669102682787, "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": 25.477272727272727, "min": 3.159090909090909, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 139.0, "max": 1382.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.159090909090909, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 139.0, "max": 1382.0, "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": "1690483287", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690483794" }, "total": 506.65969407499983, "count": 1, "self": 0.43599967799991646, "children": { "run_training.setup": { "total": 0.03485615299996425, "count": 1, "self": 0.03485615299996425 }, "TrainerController.start_learning": { "total": 506.18883824399995, "count": 1, "self": 0.6211663300023247, "children": { "TrainerController._reset_env": { "total": 5.763199587999907, "count": 1, "self": 5.763199587999907 }, "TrainerController.advance": { "total": 499.6619206959979, "count": 18203, "self": 0.30850115600742356, "children": { "env_step": { "total": 499.35341953999045, "count": 18203, "self": 361.45802722597955, "children": { "SubprocessEnvManager._take_step": { "total": 137.58025578198726, "count": 18203, "self": 1.9649040780038831, "children": { "TorchPolicy.evaluate": { "total": 135.61535170398338, "count": 18203, "self": 135.61535170398338 } } }, "workers": { "total": 0.31513653202364367, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 504.44888297300713, "count": 18203, "is_parallel": true, "self": 237.43663021500674, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00602879899997788, "count": 1, "is_parallel": true, "self": 0.0042831930002193985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017456059997584816, "count": 10, "is_parallel": true, "self": 0.0017456059997584816 } } }, "UnityEnvironment.step": { "total": 0.09692461800000274, "count": 1, "is_parallel": true, "self": 0.0007421059999614954, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005178100000193808, "count": 1, "is_parallel": true, "self": 0.0005178100000193808 }, "communicator.exchange": { "total": 0.07784186799995041, "count": 1, "is_parallel": true, "self": 0.07784186799995041 }, "steps_from_proto": { "total": 0.017822834000071452, "count": 1, "is_parallel": true, "self": 0.01548428299997795, "children": { "_process_rank_one_or_two_observation": { "total": 0.002338551000093503, "count": 10, "is_parallel": true, "self": 0.002338551000093503 } } } } } } }, "UnityEnvironment.step": { "total": 267.0122527580004, "count": 18202, "is_parallel": true, "self": 11.251477792008245, "children": { "UnityEnvironment._generate_step_input": { "total": 5.684083067002803, "count": 18202, "is_parallel": true, "self": 5.684083067002803 }, "communicator.exchange": { "total": 210.8360852509909, "count": 18202, "is_parallel": true, "self": 210.8360852509909 }, "steps_from_proto": { "total": 39.24060664799845, "count": 18202, "is_parallel": true, "self": 7.356090472027972, "children": { "_process_rank_one_or_two_observation": { "total": 31.884516175970475, "count": 182020, "is_parallel": true, "self": 31.884516175970475 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001685719998931745, "count": 1, "self": 0.0001685719998931745, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 495.8083154039598, "count": 464980, "is_parallel": true, "self": 10.848195863962701, "children": { "process_trajectory": { "total": 274.25905909999597, "count": 464980, "is_parallel": true, "self": 273.38576540199574, "children": { "RLTrainer._checkpoint": { "total": 0.873293698000225, "count": 4, "is_parallel": true, "self": 0.873293698000225 } } }, "_update_policy": { "total": 210.70106044000113, "count": 90, "is_parallel": true, "self": 80.03672869200454, "children": { "TorchPPOOptimizer.update": { "total": 130.66433174799658, "count": 4587, "is_parallel": true, "self": 130.66433174799658 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14238305799995032, "count": 1, "self": 0.0008846040000207722, "children": { "RLTrainer._checkpoint": { "total": 0.14149845399992955, "count": 1, "self": 0.14149845399992955 } } } } } } }