{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8863435387611389, "min": 0.8863435387611389, "max": 2.87099027633667, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8472.5576171875, "min": 8472.5576171875, "max": 29401.810546875, "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": 12.15700626373291, "min": 0.40668749809265137, "max": 12.15700626373291, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2370.6162109375, "min": 78.89737701416016, "max": 2444.7900390625, "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": 0.073456306643921, "min": 0.0641530686281804, "max": 0.07547895538293375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.293825226575684, "min": 0.2566122745127216, "max": 0.3726870564883118, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20422221921092154, "min": 0.0958455214117124, "max": 0.27959766417157417, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8168888768436862, "min": 0.3833820856468496, "max": 1.3979883208578707, "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": 23.863636363636363, "min": 2.909090909090909, "max": 24.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1050.0, "min": 128.0, "max": 1320.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.863636363636363, "min": 2.909090909090909, "max": 24.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1050.0, "min": 128.0, "max": 1320.0, "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": "1676412661", "python_version": "3.8.16 | packaged by conda-forge | (default, Feb 1 2023, 16:01:55) \n[GCC 11.3.0]", "command_line_arguments": "/home/flahoud/miniconda3/envs/rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.22.0", "end_time_seconds": "1676412967" }, "total": 306.4147855709307, "count": 1, "self": 0.27007266227155924, "children": { "run_training.setup": { "total": 0.026501960586756468, "count": 1, "self": 0.026501960586756468 }, "TrainerController.start_learning": { "total": 306.1182109480724, "count": 1, "self": 0.45160509552806616, "children": { "TrainerController._reset_env": { "total": 2.1148730544373393, "count": 1, "self": 2.1148730544373393 }, "TrainerController.advance": { "total": 303.48233869997784, "count": 18200, "self": 0.20690910425037146, "children": { "env_step": { "total": 303.2754295957275, "count": 18200, "self": 204.39120580116287, "children": { "SubprocessEnvManager._take_step": { "total": 98.68555756518617, "count": 18200, "self": 1.3977263742126524, "children": { "TorchPolicy.evaluate": { "total": 97.28783119097352, "count": 18200, "self": 21.41726898495108, "children": { "TorchPolicy.sample_actions": { "total": 75.87056220602244, "count": 18200, "self": 75.87056220602244 } } } } }, "workers": { "total": 0.19866622937843204, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 305.45667606638744, "count": 18200, "is_parallel": true, "self": 161.4256713585928, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016560880467295647, "count": 1, "is_parallel": true, "self": 0.0005039121024310589, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011521759442985058, "count": 10, "is_parallel": true, "self": 0.0011521759442985058 } } }, "UnityEnvironment.step": { "total": 0.020480547565966845, "count": 1, "is_parallel": true, "self": 0.0002981778234243393, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023158686235547066, "count": 1, "is_parallel": true, "self": 0.00023158686235547066 }, "communicator.exchange": { "total": 0.01896824175491929, "count": 1, "is_parallel": true, "self": 0.01896824175491929 }, "steps_from_proto": { "total": 0.000982541125267744, "count": 1, "is_parallel": true, "self": 0.0002453140914440155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007372270338237286, "count": 10, "is_parallel": true, "self": 0.0007372270338237286 } } } } } } }, "UnityEnvironment.step": { "total": 144.03100470779464, "count": 18199, "is_parallel": true, "self": 5.170735183171928, "children": { "UnityEnvironment._generate_step_input": { "total": 2.8592593921348453, "count": 18199, "is_parallel": true, "self": 2.8592593921348453 }, "communicator.exchange": { "total": 119.39275595266372, "count": 18199, "is_parallel": true, "self": 119.39275595266372 }, "steps_from_proto": { "total": 16.608254179824144, "count": 18199, "is_parallel": true, "self": 3.6189201520755887, "children": { "_process_rank_one_or_two_observation": { "total": 12.989334027748555, "count": 181990, "is_parallel": true, "self": 12.989334027748555 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011368328705430031, "count": 1, "self": 0.00011368328705430031, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 302.70592384506017, "count": 252248, "is_parallel": true, "self": 3.042625332251191, "children": { "process_trajectory": { "total": 162.59467322658747, "count": 252248, "is_parallel": true, "self": 162.20027481298894, "children": { "RLTrainer._checkpoint": { "total": 0.39439841359853745, "count": 4, "is_parallel": true, "self": 0.39439841359853745 } } }, "_update_policy": { "total": 137.0686252862215, "count": 90, "is_parallel": true, "self": 35.506590554025024, "children": { "TorchPPOOptimizer.update": { "total": 101.56203473219648, "count": 4587, "is_parallel": true, "self": 101.56203473219648 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06928041484206915, "count": 1, "self": 0.0008493517525494099, "children": { "RLTrainer._checkpoint": { "total": 0.06843106308951974, "count": 1, "self": 0.06843106308951974 } } } } } } }