{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9193317294120789, "min": 0.9193317294120789, "max": 2.8702778816223145, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8777.779296875, "min": 8777.779296875, "max": 29426.08984375, "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": 12.949409484863281, "min": 0.11097344011068344, "max": 12.949409484863281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2525.134765625, "min": 21.528846740722656, "max": 2612.91259765625, "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": 0.06591802781693724, "min": 0.06052903096344523, "max": 0.07133102808569959, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.263672111267749, "min": 0.2461917031757598, "max": 0.35665514042849794, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19371654085961043, "min": 0.11831303979681038, "max": 0.29205476835954425, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7748661634384417, "min": 0.4732521591872415, "max": 1.4152983374455395, "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": 25.727272727272727, "min": 3.1363636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 138.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.1363636363636362, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 138.0, "max": 1405.0, "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": "1703634378", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703634861" }, "total": 482.94253622299993, "count": 1, "self": 0.44431149799993364, "children": { "run_training.setup": { "total": 0.05442209099999218, "count": 1, "self": 0.05442209099999218 }, "TrainerController.start_learning": { "total": 482.443802634, "count": 1, "self": 0.6914505560099542, "children": { "TrainerController._reset_env": { "total": 3.080748420999953, "count": 1, "self": 3.080748420999953 }, "TrainerController.advance": { "total": 478.57740323599, "count": 18199, "self": 0.3118793959774848, "children": { "env_step": { "total": 478.2655238400125, "count": 18199, "self": 316.3856931640156, "children": { "SubprocessEnvManager._take_step": { "total": 161.55289624900342, "count": 18199, "self": 1.605224268988536, "children": { "TorchPolicy.evaluate": { "total": 159.9476719800149, "count": 18199, "self": 159.9476719800149 } } }, "workers": { "total": 0.32693442699348907, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 480.9515119330134, "count": 18199, "is_parallel": true, "self": 236.60706734201472, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005116841000017303, "count": 1, "is_parallel": true, "self": 0.0036608379999734098, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014560030000438928, "count": 10, "is_parallel": true, "self": 0.0014560030000438928 } } }, "UnityEnvironment.step": { "total": 0.04348936400003822, "count": 1, "is_parallel": true, "self": 0.0006430930000078661, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004580790000545676, "count": 1, "is_parallel": true, "self": 0.0004580790000545676 }, "communicator.exchange": { "total": 0.040385776999983136, "count": 1, "is_parallel": true, "self": 0.040385776999983136 }, "steps_from_proto": { "total": 0.002002414999992652, "count": 1, "is_parallel": true, "self": 0.00039096599982713087, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016114490001655213, "count": 10, "is_parallel": true, "self": 0.0016114490001655213 } } } } } } }, "UnityEnvironment.step": { "total": 244.3444445909987, "count": 18198, "is_parallel": true, "self": 11.447912406979526, "children": { "UnityEnvironment._generate_step_input": { "total": 5.964171766006984, "count": 18198, "is_parallel": true, "self": 5.964171766006984 }, "communicator.exchange": { "total": 189.57908447201066, "count": 18198, "is_parallel": true, "self": 189.57908447201066 }, "steps_from_proto": { "total": 37.35327594600153, "count": 18198, "is_parallel": true, "self": 7.044188516018039, "children": { "_process_rank_one_or_two_observation": { "total": 30.309087429983492, "count": 181980, "is_parallel": true, "self": 30.309087429983492 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021324500016817183, "count": 1, "self": 0.00021324500016817183, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.34916667499454, "count": 721259, "is_parallel": true, "self": 15.672548802988558, "children": { "process_trajectory": { "total": 261.9489423300064, "count": 721259, "is_parallel": true, "self": 261.12825342900646, "children": { "RLTrainer._checkpoint": { "total": 0.8206889009999259, "count": 4, "is_parallel": true, "self": 0.8206889009999259 } } }, "_update_policy": { "total": 194.7276755419996, "count": 90, "is_parallel": true, "self": 60.96993833299473, "children": { "TorchPPOOptimizer.update": { "total": 133.75773720900486, "count": 4584, "is_parallel": true, "self": 133.75773720900486 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09398717599992779, "count": 1, "self": 0.0009398739998687233, "children": { "RLTrainer._checkpoint": { "total": 0.09304730200005906, "count": 1, "self": 0.09304730200005906 } } } } } } }