{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9036049246788025, "min": 0.8995496034622192, "max": 2.869661331176758, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8637.5595703125, "min": 8637.5595703125, "max": 29451.333984375, "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": 12.782855987548828, "min": 0.36686068773269653, "max": 12.923311233520508, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2492.656982421875, "min": 71.17097473144531, "max": 2627.5107421875, "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": 0.06717685082392064, "min": 0.057956515272641854, "max": 0.07502064297595472, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26870740329568255, "min": 0.23182606109056741, "max": 0.3616790049949058, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19429726343528897, "min": 0.14144192672877884, "max": 0.27783015943041034, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7771890537411559, "min": 0.5657677069151154, "max": 1.3891507971520516, "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": 24.681818181818183, "min": 4.0227272727272725, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1086.0, "min": 177.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.681818181818183, "min": 4.0227272727272725, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1086.0, "min": 177.0, "max": 1403.0, "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": "1724514570", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724515051" }, "total": 481.4988993150001, "count": 1, "self": 0.4404060090000712, "children": { "run_training.setup": { "total": 0.09888515200003667, "count": 1, "self": 0.09888515200003667 }, "TrainerController.start_learning": { "total": 480.95960815399997, "count": 1, "self": 0.6180530099998691, "children": { "TrainerController._reset_env": { "total": 3.202961848999962, "count": 1, "self": 3.202961848999962 }, "TrainerController.advance": { "total": 477.03298032100014, "count": 18202, "self": 0.2996592469881989, "children": { "env_step": { "total": 476.73332107401194, "count": 18202, "self": 308.89903894500884, "children": { "SubprocessEnvManager._take_step": { "total": 167.52161372300304, "count": 18202, "self": 1.577731082007574, "children": { "TorchPolicy.evaluate": { "total": 165.94388264099547, "count": 18202, "self": 165.94388264099547 } } }, "workers": { "total": 0.3126684060000571, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 479.6329891429989, "count": 18202, "is_parallel": true, "self": 242.45333338400002, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.012234589999991385, "count": 1, "is_parallel": true, "self": 0.009672253000076125, "children": { "_process_rank_one_or_two_observation": { "total": 0.00256233699991526, "count": 10, "is_parallel": true, "self": 0.00256233699991526 } } }, "UnityEnvironment.step": { "total": 0.04049730599996337, "count": 1, "is_parallel": true, "self": 0.0006836909999492491, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004500750000033804, "count": 1, "is_parallel": true, "self": 0.0004500750000033804 }, "communicator.exchange": { "total": 0.03719612100002223, "count": 1, "is_parallel": true, "self": 0.03719612100002223 }, "steps_from_proto": { "total": 0.002167418999988513, "count": 1, "is_parallel": true, "self": 0.0003967549999970288, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017706639999914842, "count": 10, "is_parallel": true, "self": 0.0017706639999914842 } } } } } } }, "UnityEnvironment.step": { "total": 237.17965575899888, "count": 18201, "is_parallel": true, "self": 10.556524119993526, "children": { "UnityEnvironment._generate_step_input": { "total": 5.869141032994321, "count": 18201, "is_parallel": true, "self": 5.869141032994321 }, "communicator.exchange": { "total": 184.50387777900727, "count": 18201, "is_parallel": true, "self": 184.50387777900727 }, "steps_from_proto": { "total": 36.25011282700376, "count": 18201, "is_parallel": true, "self": 6.9314660970222235, "children": { "_process_rank_one_or_two_observation": { "total": 29.318646729981538, "count": 182010, "is_parallel": true, "self": 29.318646729981538 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013917000001129054, "count": 1, "self": 0.00013917000001129054, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.78518024799354, "count": 708950, "is_parallel": true, "self": 15.586997368978473, "children": { "process_trajectory": { "total": 261.43889238601497, "count": 708950, "is_parallel": true, "self": 260.7114087450148, "children": { "RLTrainer._checkpoint": { "total": 0.7274836410001626, "count": 4, "is_parallel": true, "self": 0.7274836410001626 } } }, "_update_policy": { "total": 193.7592904930001, "count": 90, "is_parallel": true, "self": 61.56057751600389, "children": { "TorchPPOOptimizer.update": { "total": 132.1987129769962, "count": 4587, "is_parallel": true, "self": 132.1987129769962 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10547380399998474, "count": 1, "self": 0.0009808869999687886, "children": { "RLTrainer._checkpoint": { "total": 0.10449291700001595, "count": 1, "self": 0.10449291700001595 } } } } } } }