{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9046974778175354, "min": 0.9046974778175354, "max": 2.858578681945801, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8608.1962890625, "min": 8608.1962890625, "max": 29274.705078125, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.193910598754883, "min": 0.49735403060913086, "max": 13.193910598754883, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2559.61865234375, "min": 96.48667907714844, "max": 2690.6064453125, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09973442410980579, "min": 0.09419775114559764, "max": 0.10197280512037134, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.39893769643922317, "min": 0.37679100458239057, "max": 0.5049093721862566, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.26513606062755474, "min": 0.19741085787176654, "max": 0.37160384447551237, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.060544242510219, "min": 0.7896434314870662, "max": 1.8580192223775618, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.9152980848000005e-06, "min": 1.9152980848000005e-06, "max": 9.78352021648e-05, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.661192339200002e-06, "min": 7.661192339200002e-06, "max": 0.00046937603062400005, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1019152, "min": 0.1019152, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4076608, "min": 0.4076608, "max": 0.9693759999999998, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000005, "min": 0.00010556848000000005, "max": 0.00489197648, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004222739200000002, "min": 0.0004222739200000002, "max": 0.0234718624, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.272727272727273, "min": 4.2727272727272725, "max": 26.272727272727273, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1156.0, "min": 188.0, "max": 1427.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.272727272727273, "min": 4.2727272727272725, "max": 26.272727272727273, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1156.0, "min": 188.0, "max": 1427.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718983033", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718984045" }, "total": 1011.4148098920004, "count": 1, "self": 0.7029310090010767, "children": { "run_training.setup": { "total": 0.05215401999976166, "count": 1, "self": 0.05215401999976166 }, "TrainerController.start_learning": { "total": 1010.6597248629996, "count": 1, "self": 0.6863946979883622, "children": { "TrainerController._reset_env": { "total": 2.0643837919997168, "count": 1, "self": 2.0643837919997168 }, "TrainerController.advance": { "total": 1007.7137559050116, "count": 22749, "self": 0.34114335602316714, "children": { "env_step": { "total": 1007.3726125489884, "count": 22749, "self": 814.0623557951249, "children": { "SubprocessEnvManager._take_step": { "total": 192.95962852390767, "count": 22749, "self": 1.848402433969568, "children": { "TorchPolicy.evaluate": { "total": 191.1112260899381, "count": 22749, "self": 191.1112260899381 } } }, "workers": { "total": 0.3506282299558734, "count": 22749, "self": 0.0, "children": { "worker_root": { "total": 1008.9884122890226, "count": 22749, "is_parallel": true, "self": 731.7692877090494, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023536250000688597, "count": 1, "is_parallel": true, "self": 0.0006906180005898932, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016630069994789665, "count": 10, "is_parallel": true, "self": 0.0016630069994789665 } } }, "UnityEnvironment.step": { "total": 0.03974791499967978, "count": 1, "is_parallel": true, "self": 0.0006456249984694296, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037757400059490465, "count": 1, "is_parallel": true, "self": 0.00037757400059490465 }, "communicator.exchange": { "total": 0.03654908299995441, "count": 1, "is_parallel": true, "self": 0.03654908299995441 }, "steps_from_proto": { "total": 0.002175633000661037, "count": 1, "is_parallel": true, "self": 0.0004665080004997435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017091250001612934, "count": 10, "is_parallel": true, "self": 0.0017091250001612934 } } } } } } }, "UnityEnvironment.step": { "total": 277.21912457997314, "count": 22748, "is_parallel": true, "self": 12.893571970917037, "children": { "UnityEnvironment._generate_step_input": { "total": 6.783777409101276, "count": 22748, "is_parallel": true, "self": 6.783777409101276 }, "communicator.exchange": { "total": 214.5243767519305, "count": 22748, "is_parallel": true, "self": 214.5243767519305 }, "steps_from_proto": { "total": 43.01739844802432, "count": 22748, "is_parallel": true, "self": 8.238790467246872, "children": { "_process_rank_one_or_two_observation": { "total": 34.77860798077745, "count": 227480, "is_parallel": true, "self": 34.77860798077745 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001118219997806591, "count": 1, "self": 0.0001118219997806591, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1000.595227553179, "count": 844558, "is_parallel": true, "self": 18.986333785509487, "children": { "process_trajectory": { "total": 313.3554491666673, "count": 844558, "is_parallel": true, "self": 311.3775110406659, "children": { "RLTrainer._checkpoint": { "total": 1.9779381260013906, "count": 5, "is_parallel": true, "self": 1.9779381260013906 } } }, "_update_policy": { "total": 668.2534446010022, "count": 113, "is_parallel": true, "self": 168.80700590504057, "children": { "TorchPPOOptimizer.update": { "total": 499.44643869596166, "count": 34569, "is_parallel": true, "self": 499.44643869596166 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19507864600018365, "count": 1, "self": 0.004157746000601037, "children": { "RLTrainer._checkpoint": { "total": 0.19092089999958262, "count": 1, "self": 0.19092089999958262 } } } } } } }